САМОУПРАВЛЯЕМЫЕ ЗАРЯДНЫЕ СТОЙКИ

Группа изобретений относится к зарядке аккумуляторов электрического транспортного средства. Способ планирования зарядки электрического транспортного средства заключается в следующем. Принимают запрос на зарядку от электрического транспортного средства на зарядной стойке. Определяют отрезок времени зарядки для электрического транспортного средства на основе запроса на зарядку. Вносят в расписание отрезок времени зарядки для электрического транспортного средства. Прогнозируют требование по нагрузке для зарядной стойки на основе запроса на зарядку и отрезка времени зарядки. Отправляют требование по нагрузке оператору сети, снабжающему зарядную стойку электрической мощностью. Зарядная стойка содержит зарядное устройство, устройство связи и вычислительное устройство, выполненное с возможностью управлять зарядкой и выполнять способ планирования зарядки электрического транспортного средства. Зарядная система содержит множество зарядных стоек, соединенных с возможностью связи по сети передачи данных ...

СПОСОБ И МОДУЛЬ ДЛЯ ОПРЕДЕЛЕНИЯ ОПОРНЫХ ЗНАЧЕНИЙ ДЛЯ СИСТЕМЫ УПРАВЛЕНИЯ ТРАНСПОРТНОГО СРЕДСТВА

... 1. Способ определения по меньшей мере одного опорного значения для системы управления транспортным средством, отличающийся тем, что содержит этапы:- получения заданной скорости vset для транспортного средства;- определения для маршрута, посредством картографических данных и данных о местоположении, горизонта, который содержит один или более сегментов маршрута с по меньшей мере одной характеристикой для каждого сегмента;- выполнения во время каждого из множества циклов sмоделирования, каждый из которых содержит множество N стадий моделирования, выполняемых с предопределенной скоростью f, следующих стадий:- создания первого прогноза скорости транспортного средства vвдоль горизонта в соответствии с обычным круиз-контролем, когда заданная скорость vиспользуется в качестве опорной скорости v, причем первый прогноз зависит от характеристик упомянутого сегмента маршрута;- выполнения первого сравнения первой прогнозируемой скорости транспортного средства vс по меньшей мере одним из первых нижнего ...

Verfahren und Vorrichtung zum Herstellen eines Bauteils aus Glas durch Ziehen aus einem Rohling

A microgrid control apparatus method and system for controlling energy flow within a microgrid

Method for determining and using a climate energy index

CASCADED CONTROLLING OF AN AVERAGE VALUE OF A PROCESS PARAMETER TO A DESIRED VALUE

UNIVERSAL PROCEDURE FOR THE PREDETERMINATION OF PARAMETERS INDUSTRIALISTS OF PROCESSES

Acoustic pressure shock waves used for personalized medical treatment of tissue conditions

A system for individualized treatment of a tissue condition with acoustic pressure shocks includes personalized determination and automatic adjustment of a shock wave treatment regimen or shock wave dosage to be administered for personalized treatment based on factors such as a patients comorbidities, state of the tissue condition, individual physical characteristics and lifestyle parameters.

IoT and Machine Learning based Building Energy Management System (iBEMS)

... "IoT and Machine Learning based Building Energy Management System (iBEMS)" Exemplary aspects of the present disclosure are directed towards the IoT and Machine Learning based Building Energy Management System (iBEMS) which typical consists of plurality of IoT based Remote Management Terminals (iRMT) 101 installed in every distribution board (DB) of a building/commercial complex for power measurement and control. Wherein iRMT constitutes Noninvasive Current-Transformers (CTs) 101c and Potential-Transformers (PTs) 101d hooked up to ADE7816 Power IC 101b. iRMTs 101 send the power data to Main central console (iBEMS MAIN) 103 through Wi-Fi/RF 102 and there from there to user through in-build GSM700 module 103b. iRMTs executes relevant Machine-Learning Algorithms for suitably processing and storing the data for future analysis and for executing control strategies including the control of the Modular case circuit breaker (MCCB's) 101e. Main central console (iBEMS MAIN)103 executes relevant Machine-Learning ...

GAS LIQUEFACTION PROCESS CONTROL SYSTEM

SYSTEMS AND METHODS FOR OPTIMIZING ENERGY USAGE USING ENERGY DISAGGREGATION DATA AND TIME OF USE INFORMATION

The present invention is generally directed to systems and methods for optimizing energy usage in a household. For example, methods for optimizing energy usage in a household may include steps of: receiving, using an energy optimization device, entire energy profile data associated with the household; obtaining, using the energy optimization device, time of use (TOU) energy pricing structure; processing, the entire energy profile data to generate disaggregated appliance level data related to one or more appliances used in the household; retrieving historical patterns of energy usage of the household during both peak and non-peak time periods; applying a behavior shift analysis on the disaggregated data based at least in part on the TOU energy pricing structure, disaggregated data, and historical patterns of the energy usage; and predicting potential energy savings based at least in part on the behavior shift analysis.

DIAGNOSTICS IN BUILDING AUTOMATION

Using data from various sources, clustering (52) or other unsupervised learning determines a relationship of the data to performance. Meta data or business data different than building automation data is used to diagnose building automation. Relationships of building automation to the meta or business data are determined with clustering (52) or other case-based reasoning. For multiple building situations, clustering (52) with or without the meta data identifies poor performing buildings, equipment, automation control, or enterprise function.

SYSTEM FOR OPTIMIZATION OF BUILDING HEATING AND COOLING SYSTEMS

A method of designing an optimized heating and cooling system includes: (1) automatically importing data from an energy model into an optimization model; (2) simulating energy use of a virtual heating and cooling system operating a thermal source or sink with the optimization model based upon the data from the energy model to obtain an optimized system design; (3) developing controls for an actual heating and cooling system based upon the optimized system design; and (4) automatically exporting the controls directly to a controller for the actual heating and cooling system.

OPTIMIZING AND CONTROLLING THE ENERGY CONSUMPTION OF A BUILDING

Described herein are methods and systems, including computer program products, for optimizing and controlling the energy consumption of a building. A first computing device generates a set of thermal response coefficients for the building based on energy characteristics of the building and weather data associated with the location of the building. The first computing device predicts an energy response of the building based on the set of thermal response coefficients and forecasted weather associated with the location of the building. The first computing device selects minimal energy requirements of the building based on an energy consumption cost associated with the building. The first computing device determines one or more temperature set points for the building based on the energy response and the minimal energy requirements. The first computing device transmits the one or more temperature set points to a thermostat of the building.

GAS LIQUEFACTION PROCESS CONTROL SYSTEM

PATENT - 211PUS03923 A method for controlling the operation of a liquefied natural gas (LNG) process which utilizes gas turbine-driven refrigeration compressors is disclosed. A feedforward control system compensates for the effects of changes in ambient air temperature on the plant operating efficiency by periodically predicting a new temperature and resetting the set points of key feedback controllers in anticipation of this new temperature, thereby optimizing the operation of the plant and minimizing the specific fuel consumption at a given LNG production rate.

Brain-based device having a cerebellar model for predictive motor control

A mobile brain-based device (BBD) includes a mobile platform with sensors and effects, which is guided by a simulated nervous system that is an analogue of the cerebellar areas of the brain used for predictive motor control to determine interaction with a real-world environment. The simulated nervous system has neural areas including precerebellum nuclei (PN), Purkinje cells (PC), deep cerebellar nuclei (DCN) and an inferior olive (IO) for predicting turn and velocity control of the BBD during movement in a real-world environment. The BBD undergoes training and testing, and the simulated nervous system learns and performs control functions, based on a delayed eligibility trace learning rule.

Method for predictive determination of a process variable

A system and method are disclosed for predictive determination of a process variable (P) in a technical installation. Measured values for the process variable (P) are recorded at predeterminable points in time. Temporally successive recorded measured values are combined to form a weighted measured value. A discrete measured value is assigned to each weighted measured value. A future temporal progression of the process variable (P) is estimated using a linear regression of the discrete measured values, and a point in time in which the process variable (P) reaches a predeterminable limit value is calculated.

NUMERICAL PROCESS OF REGULATION USING a PROCESS Of OBSERVATION OR MONITORING

USE OF SIMULATION TO GENERATE PREDICTIONS PERTAINING TO A MANUFACTURING FACILITY

ENERGY-OPTIMAL CONTROL DECISIONS FOR HVAC SYSTEMS

Search apparatus and search method

An object of the present invention is to achieve an efficient operation in a semiconductor treatment apparatus. In order to accomplish the above object, there is provided a retrieval apparatus including a processor and a memory for retrieving conditions for a semiconductor treatment apparatus. The processor receives a processing result of a semiconductor being treated by the semiconductor treatment apparatus, a condition corresponding to the processing result, a target value for treating the semiconductor in the semiconductor treatment apparatus, and a retrieval region, generates a prediction model indicating a relationship between the condition and the processing result on the basis of a set value of the condition in the retrieval region, and the processing result in a case where the set value is given to the semiconductor treatment apparatus, calculates a predicted value by giving the received target value to the prediction model, performs a demonstration test based on the predicted value ...

A METHOD AND APPARATUS FOR AUTOMATION OF A PROGRAMMABLE DEVICE

A method and apparatus for a computer-implemented adaptive automation module comprising an event recorder to store one or more events for a predetermined period, and a timeline pattern generator logic to create a timeline for the predetermined period. The module further comprising marker creator logic to generate a marker to abstract the timeline data from the event data for controlling a device.

Building energy storage system with peak load contribution cost optimization

An energy storage system for a building includes a battery and an energy storage controller. The battery is configured to store electrical energy purchased from a utility and to discharge stored electrical energy for use in satisfying a building energy load. The energy storage controller is configured to generate a cost function including a peak load contribution (PLC) term. The PLC term represents a cost based on electrical energy purchased from the utility during coincidental peak hours in an optimization period. The controller is configured to modify the cost function by applying a peak hours mask to the PLC term. The peak hours mask identifies one or more hours in the optimization period as projected peak hours and causes the energy storage controller to disregard the electrical energy purchased from the utility during any hours not identified as projected peak hours when calculating a value for the PLC term.

CLIMATE CONTROL ADAPTIVE TEMPERATURE SETPOINT ADJUSTMENT SYSTEMS AND METHODS

The present disclosure presents techniques for improving operational efficiency of climate control systems. A climate control system may include climate control equipment, a sensor that measures temperature in a building, and a control system that controls operation of the equipment using a first temperature schedule, which associates each time step with a temperature setpoint, when the building is occupied. When not occupied, the control system determines an expected return time based on historical occupancy data associated with the building, determines the temperature setpoint associated with the expected return time, determines candidate schedules each expected to result in the inside air temperature meeting the temperature setpoint, determines efficiency metrics each associated with one of the candidates based on historical performance data resulting from previous operation of the climate control system, and controls operation of the equipment based on a second temperature schedule ...

Energy-optimal control decisions for systems

Methods, systems, and apparatuses are provided for controlling an environmental maintenance system that includes a plurality of sensors and a plurality of actuators. The operation levels of the actuators can be determined by optimizing a penalty function. As part of the penalty function, the sensor values can be compared to reference values. The optimized values of the operation levels can account for energy use of actuators at various operation levels and predicted differences of the sensor values relative to the reference values at various operation levels. The predicted difference can be determined using a transfer model. An accuracy of the transfer model can be determined by comparing predicted values to measured values. This accuracy can be used in determining new operational levels from an output of the transfer model (e.g., attenuating the output of the transfer model based on the accuracy).

System of case-based reasoning for sensor prediction in a technical process, especially in a cement kiln, method and apparatus therefore

A system of case-based reasoning for sensor prediction in a technical process, especially in a cement kiln, method and apparatus therefore, and wherein the system provides accurate predictions of the cement kiln behavior for a limited period into the future. The invention utilizes a method of case-base-reasoning (CBR) for the task of sensor value prediction. An apparatus for implementing the method is characterized by a database (100) in which the relevant time interval data are stored, a test generator (101) and an optimisation unit (102- 104) for the selection and optimisation of the time interval data.

POWER DEMAND FORECAST DEVICE, METHOD AND SYSTEM AND POWER FAILURE DETECTION SYSTEM

Disclosed herein is a power demand forecast device including: an absence detection section adapted to detect whether a consumer is absent at a given location; and a power demand forecast section adapted to forecast a power demand on a forecasted date and time in future based on an absence detection result obtained by the absence detection section.

EMBEDDED DYNAMIC STABILITY MEASUREMENT, OPTIMIZATION AND ALARM SYSTEM

An intelligent load control device is provided for operable incorporation in an object. The intelligent load control device includes devices disposed about the object to detect characteristics thereof that are relevant to an object tipping event, a response system, and a processing unit. The response system is configured to take an action to mitigate risks associated with the object tipping event responsive to received control instructions. The processing unit is disposed to be receptive of the detected characteristics from the devices and to issue the control instructions to the response system. The processing unit is configured to dynamically analyze the detected characteristics to determine a likelihood of the object tipping event and to issue the control instructions in accordance with the determined likelihood.

Adaptive sensor data selection and sampling based on current and future context

A method for controlling a sensor may be performed by a mobile device including a processor and a memory. The method may include receiving raw data from the sensor, classifying the raw data into a context value, interpreting the context value into a higher-level context, receiving a predicted context based on the higher-level context, and controlling the sensor based on the predicted context. Controlling the sensor may include controlling a frequency at which raw data is received from the sensor, or an on/off state of the sensor. Control of the sensor may also be based on both the higher-level context and the predicted context.

Building energy optimization system with automated and dynamic economic load demand response (ELDR) optimization

An energy optimization system for a building includes a processing circuit configured to provide a first bid including one or more first participation hours and a first load reduction amount for each of the one or more first participation hours to a computing system. The processing circuit is configured to operate one or more pieces of building equipment based on one or more first equipment loads and receive one or more awarded or rejected participation hours from the computing system responsive to the first bid. The processing circuit is configured to generate one or more second participation hours, a second load reduction amount for each of the one or more second participation hours, and one or more second equipment loads based on the one or more awarded or rejected participation hours and operate the one or more pieces of building equipment based on the one or more second equipment loads.

METHODS AND SYSTEMS FOR ENHANCING CONTROL OF POWER PLANT GENERATING UNITS

A method for optimizing a generation of an output level over a selected operating period by a power block (860,902), wherein the power block comprises multiple gas turbines for collectively generating the output level, the control method including the steps of: receiving current state data regarding measured operating parameters for each of the gas turbines of the power block (860,902); based on the current state data, defining competing operating modes for the power block (860,902), wherein each of the competing operating modes comprises a unique generating configuration for the power block (860,902); based on the generating configurations of each of the competing operating modes, deriving a predicted value for a performance parameter regarding the operation of the power block (860,902) over the selected operating period; determining a cost function and, pursuant thereto, evaluating the operation of the power block (860,902) based on the predicted value of the performance parameter so ...

Plant control system with disturbance compensation

A plant control system provides an enhanced capability of compensation for disturbance that abruptly changes. A controller includes a disturbance predictor for calculating a predicted value of disturbance on the basis of a drag force of a release spring and an assisting force of a compensation spring that are predicted on the basis of a clutch stroke, an adaptive disturbance observer for calculating an estimated value of disturbance on the basis of the estimated value of disturbance, a voltage to be applied to a motor, and the clutch stroke, and a sliding mode controller, which determines the voltage to be applied to the motor by carrying out control for making the clutch stroke follow a clutch stroke target value by determining the voltage to be applied to the motor by sliding mode control on the basis of the clutch stroke, the predicted value of disturbance, and the estimated value of disturbance.

Control apparatus, control method, and engine control unit

A control apparatus is provided for eliminating a slippage in control timing between the input/output of a controlled object, even when the control object exhibits a relatively large dynamic characteristic such as a phase delay, a dead time, or the like, to improve the stability and the controllability of the control. The control apparatus comprises a state predictor for calculating a predicted value of a value indicative of an output of a controlled object based on a prediction algorithm, and a DSM controller for calculating a control input to the controlled object based on one modulation algorithm selected from a Δ modulation algorithm, a ΔΣ modulation algorithm, and a ΣΔ modulation algorithm for controlling the output of the controlled object in accordance with the calculated predicted value.

INDUSTRIAL CONTROL SYSTEM AND METHOD FOR OPERATING AN INDUSTRIAL CONTROL SYSTEM

Die Erfindung betrifft ein Verfahren zum Betrieb einer industriellen Steuerungsanlage (1) umfassend eine Automatisierungssteuerung (CPU) mit einem Ablaufprogramm (OB1), einem Ansteuermittel (2) ausgestaltet zum Ansteuern einer Schaltkomponente (SR) der Leistungselektronik und eine Eingabebaugruppe (EA), wobei durch Ein- und Ausschaltvorgänge (EV,AV) der Schaltkomponente (SR) Elektromagnetische Störungen (EMI) auftreten, welche einen über die Eingabebaugruppe (EA) aufgenommenen Messwert (MW) verfälschen, wobei für die Schaltkomponente (SR) ein zeitliches Auftreten der Ein- und Ausschaltvorgänge (EV,AV) und/oder ein Betriebszustand (BZ) vorhergesagt wird, wobei die Vorhersage dazu genutzt wird eine Korrektur des Messwertes (MW) zu einem Vorhersagezeitpunkt oder während einem Vorhersage-Zeitbereich (VZB) bezüglich der Verfälschung durch die Elektromagnetische Störung (EMI) durchzuführen.

УСОВЕРШЕНСТВОВАННЫЙ КОНТРОЛЛЕР СОСТОЯНИЯ СИСТЕМЫ, УПРАВЛЯЕМОЙ ПРИ ПОМОЩИ КОМАНДЫ

Группа изобретений относится к комплексу и способу для контроля состояния системы. Комплекс содержит систему, контроллер состояния системы. Контроллер состояния содержит вычислительное устройство и память. Для контроля состояния системы определяют максимальное число рабочих режимов системы, определяют набор записанных в памяти функций состояния, представляющих для каждого рабочего режима системы значение проекции ее состояния во времени, сохраняют в памяти функции состояния так, чтобы во время работы системы при помощи вычислительного устройства определять оценочные значения состояния системы в данный момент при помощи функций состояния и ее состояния в предшествующий момент. Обеспечивается непрерывный контроль состояния различных систем. 2 н. и 8 з.п. ф-лы, 3 ил.

УСТРОЙСТВО УПРАВЛЕНИЯ ЭЛЕКТРОПРИВОДОМ ОЧИСТНОГО КОМБАЙНА

Полезная модель относится к горной промышленности, и может быть использована в системах автоматического регулирования и управления электроприводами угольных комбайнов для повышения их надежности и производительности, путем применения нейронных сетей. Техническим результатом заявляемой полезной модели является повышение надежности эксплуатации и производительности очистного комбайна. Устройство управления электроприводом очистного комбайна, включающее два асинхронных электродвигателя резания, два асинхронных электродвигателя подачи, содержит датчик тока двигателей резания, преобразователь частоты, регулятор нагрузки, блок сравнения, блок задания тока двигателей резания, блок контроля и прогнозирования параметров элементов электропривода, блок датчиков, блок пороговых сигналов и блок сигнализации. Устройство позволяет прогнозировать состояние рабочего инструмента очистных комбайнов без его остановки. По результатам прогноза выдаются упреждающие рекомендации по техническому обслуживанию электропривода ...

САМОУПРАВЛЯЕМЫЕ ЗАРЯДНЫЕ СТОЙКИ

Steuereinrichtung

Eine Steuereinrichtung enthält eine Steuereinheit eines Steuerobjektes, eine Erfassungseinheit für einen Ausgabewert eines Steuerobjektes, eine Einstelleinheit für einen Ausgabesollwert eines Steuerobjektes, eine Berechnungseinheit für einen Steuereingangswert, eine Berechnungseinheit für einen Ausgabezielreaktionswert eines Steuerobjektes, eine Berechnungseinheit für einen Ausgaberückkopplungssteuereingangswert eines Steuerobjektes und ein Schätzungsmittel für einen Ausgabevorwärtskopplungssteuereingangswert eines Steuerobjektes. Wenn der Ausgabezielwert durch die Einstelleinheit des Ausgabesollwertes geändert wird, wird ein Berechnungsverfahren zum Berechnen des Ausgabesollreaktionswertes geändert in den Fällen, in denen ein Ausgabesollwert nach Änderung größer eingestellt ist als vor der Änderung, und in denen er kleiner eingestellt ist, und eine Übergangsreaktion des Ausgabesollwertes wird unterschieden zwischen Fällen, in denen der Ausgabesollwert vergrößert ist und in denen er verkleinert ...

Fahrzeugenergie-Managementsystem, welches Vorhersagen verwendet

Energiemanagementsystem (10) zum Steuern eines elektrischen Systems, umfassend: Datenerfassungskomponenten (29, 31, 45), welche quantifizierte Variablen zum Bilden eines Momentanzustandsvektors liefern; einen Zeitserienprädiktor (30), welcher einen geschätzten Zukunftsvektorwert in Reaktion auf den Momentanzustandsvektor erzeugt, wobei der Zeitserienprädiktor (30) ein künstliches neuronales Netzwerk umfasst. einen elektrischen Systemmanager (11) mit vorbestimmten Entscheidungsregeln, welche abgerufen werden in Reaktion auf den geschätzten Zukunftsvektorwert, um das elektrische System an erwartete elektrische Bedingungen anzupassen, dadurch gekennzeichnet, dass der Zeitserienprädiktor (30) einen Speicherpuffer (33) umfasst, welcher verbunden ist mit dem künstlichen neuronalen Netzwerk (32) für ein Zeitabtasten von Inhalten des künstlichen neuronalen Netzwerks (32) und Liefern der zeitabgetasteten Inhalte an das künstliche neuronale Netzwerk (32), wenn ein anschließender geschätzter Zukunftsvektorwert ...

Method and system for integrated analysis

A system and method of analysis, including, but not limited to: receiving raw data related to at least one project; receiving user preferences in at least one workflow, wherein each step in the a workflow constitutes a single instance of a component of a workflow such that the state of a unique component is always the same if the same component is comprised in other workflows; determining metrics related to the at least one project; analyzing the data & metrics to identify patterns; drawing conclusions from the data, metrics and patterns; and generating at least one report that presents the metrics, patterns and conclusions.

Catalyst monitor

In a system to monitor the activity of the catalytic convertor in the exhaust pipe of an ic engine, the level of emissions Pf Pt in the catalyst feedpipe and tailpipe are predicted from engine operating conditions 48 and the catalyst activity is determined by comparison of the ratio R of the predicted emission levels with a predetermined standard T. The predictions PfPt are carried out by neural networks 44, 46 which are trained by inputting data acquired from performance evaluation of a plurality of vehicles having the same engine-type but differing in their degree of deterioration. ...

Systems and methods for enabling quick cold starting

Method and system of monitoring appliance usage

MULTI-SIZE PROCESS TAX METHOD AND EQUIPMENT

PROCEDURE FOR THE FORESIGHTED DETERMINATION OF A PROCESS VARIABLE

PROCEDURE FOR THE REGULATION OF DIFFERENTIAL DOSING SCALES, IN PARTICULAR FOR BULK MATERIALS, AND DIFFERENTIAL DOSING SCALES FOR THE EXECUTION OF THE PROCEDURE.

METHOD FOR THE OPERATION OF A TECHNICAL SYSTEM

Adaptive system for predictive control of district pressure regulators

Multivariable process control method and apparatus

Systems and methods for enabling quick cold starting

A method of reducing cold startup time of a genset includes providing a lubricant to the genset at predetermined time intervals before a genset startup. The lubricant is heated to a predetermined lubricant temperature using an external heating system. A high temperature coolant of the genset is heated to greater than a predetermined high temperature coolant temperature. The speed of the engine is ramped to a target speed continuously without pausing at a speed lower than the target speed. Genset electrical parameters of the genset are synchronized to utility grid or load electrical parameters of the utility grid or load. The genset is electrically coupled to the utility grid or load such that the synchronizing and electrically coupling are performed within a predetermined synchronization time. A fueling rate and a spark timing is adjusted based on a power being produced by the genset.

A attack detection algorithm based on Bayesian in adversarial network environment

Abstract: In this patent, we study the problem of multi-task parameter estimation in the adversarial environment of wireless sensor networks. According to the multi-task network environment, an attack model constructed based on the similarity between tasks is considered. In order to solve this attack, the TMDLMS algorithm is proposed. The state of the device is judged by the local estimation value obtained by the non cooperative LMS (NCLMS) system and the Bayes algorithm are used as an attack detection mechanism. At the same time, through the stability analysis and simulation experiment of the algorithm mean square and mean square, the effectiveness of the algorithm in the adversarial network environment is verified. Fig .2 Detection ,ate Judgment 7" = 0 f , > 8 BaIesian n P, I E U w p DLMSB 9. (w!%'pz) rDLMScomputea ja combine (iC LMS Combination Exchange Adaption ...

A METHOD OF IMPROVING RESILIENCE IN EMBEDDED IOT NETWORKS BY FAULT FORECASTING

A METHOD OF IMPROVING RESILIENCE IN EMBEDDED IOT NETWORKS BY FAULT FORECASTING Everything that is around us today is automized with the internet of things. The automization requires resilience in embedded internet of things network, which in turn require a fault forecasting to sustain the quality of service. The status of the service is recorded in the cloud through the gateway, and the user can monitor the automization service. This invention provides a method of improving resilience in an embedded IoT where sensors and the cameras are deployed to get the information either the statistical or the image data. The data are computed by resilience embedded internet of things with high end computing resources. The extracted data are deployed by fault forecast to eliminate a problem before it happens and also respond to it after it happened. The status of the service is also recorded in the cloud through the gateway, and the user can monitor the automization service. This improved method of ...

PREDICTION IN BUILDING AUTOMATION

Degraded or other performance may be predicted with a machine-learnt classifier. Based on operation of many building automation systems, machine learning is applied. The machine learning creates a predictor. The machine- learnt predictor is applied to the operation data of any building automation system to predict future failure or other event, providing prognostics that may be used to plan maintenance and/or schedule remedial action. Machine learning uses big data in the form of data from many building automation systems to learn to automatically predict and/or perform prognostics for other building automations systems.

A BATTERY STATE MONITORING SYSTEM AND METHOD THEREFOR

The present disclosure envisages an on-board battery state monitoring system for monitoring state of charge of a battery of an electric vehicle. The system comprises an onboard processor in data communication with a central server of a transit agency; at least one CAN network for monitoring different parameters of the electric vehicle; a recharge module configured to analyze Parameter Group Numbers (PGNs) in messages broadcasted by the at least one CAN network and filter out PGNs that provide state of charge of the battery, wherein the filtered out PGNs are transmitted to the on-board processor for the state of charge analysis of the battery to determine if an electric vehicle block can be completed.

DIAGNOSTICS IN BUILDING AUTOMATION

SYSTEMS AND METHODS FOR REAL-TIME FORECASTING AND PREDICTING OF ELECTRICAL PEAKS AND MANAGING THE ENERGY, HEALTH, RELIABILITY, AND PERFORMANCE OF ELECTRICAL POWER SYSTEMS BASED ONAN ARTIFICIAL ADAPTIVE NEURAL NETWORK

A system for utilizing a neural network to make real-time predictions about the reliability and performance of a monitored system are disclosed The system includes a data acquisition component, a power analytics server and a client terminal The data acquisition component acquires real-time data output from the electrical system The power analytics server is comprised of a virtual system modeling engine, an analytics engine, an adaptive prediction engine The virtual system modeling engine gener-ates predicted data output for the electrical system The analytics engine monitors real-time data output and predicted data output of the electrical system The adaptive prediction engine can be configured to forecast an aspect of the monitored system using a neural network algorithm The adaptive prediction engine is further configured to process the real-time data output and optimize the neural network algorithm by minimizing a measure of error between real-time data output and an estimated data output ...

DIAGNOSTICS IN BUILDING AUTOMATION

Control device, control method and engine control unit

NUMERICAL PROCESS OF REGULATION USING a PROCESS Of OBSERVATION OR MONITORING

CONTROL DEVICE OF PROCESS

PROCESS AND SYSTEM OF PROCESS CONTROL

Refrigeration cycle control device for vehicle, has target temperature output response value calculation unit in which target output response value calculating process is modified, when target temperature output of evaporator is modified

Un dispositif de commande notamment pour un système de climatisation de véhicule, comprend un moyen de commande de l'objet de commande, un moyen de détection de la valeur de sortie de l'objet de commande, un moyen de fixation de la valeur cible de sortie de l'objet de commande, un moyen de calcul de la valeur d'entrée de commande, un moyen de calcul de la valeur de réponse cible de sortie de l'objet de commande, un moyen de calcul de la valeur d'entrée de commande à asservissement de sortie de l'objet de commande et un moyen d'estimation de la valeur d'entrée de commande prédictive de sortie de l'objet de commande. Lorsque la valeur cible de sortie est modifiée par le moyen de fixation de la valeur cible de sortie de l'objet de commande, un procédé de calcul calculant la valeur de réponse cible de sortie est modifié, au cas où une valeur cible de sortie après modification est fixée plus grande, ou plus petite, que celle avant modification, et une réponse transitoire de la valeur cible de ...

SIMULATION USE FOR GENERATING PREDICTION RELATED TO A MANUFACTURING FACILITY BY USING A SIMULATION MODEL

PURPOSE: The simulation use for generating prediction related to a manufacturing facility is provided to predict a schedule for the facility by constructing a simulation model based on the obtained data about the current state of the manufacturing facility. CONSTITUTION: Data about a current state of a manufacturing facility or a component is obtained(302). A simulation model is constructed based on the data about the current state of the manufacturing facility(304). The time horizon limiting one point of the future is determined(306). A simulation operation for the timing is performed by using the simulation model for predicting the state of a part of the manufacturing facility or more in the point of the future(308). Each transition of a product, equipment, an operator, a tool or other units is recorded(310). The calculated prediction is stored in a database(312). © KIPO 2009 ...

CONTROL DEVICE OF INTERNAL COMBUSTION ENGINE

Disclosed is a control device of an internal combustion engine provided with means for correcting a target value of each object to be controlled; means for predicting the future state related with each of the objects when each of the objects is controlled according to an initial target value or a corrected target value of the object; and means for discriminating between whether or not the predicted future state related with each of the objects satisfies constraint conditions related with the internal combustion engine; wherein until a discrimination is made that the predicted future state related with each of the objects satisfies the constraint conditions, a correction of the target value of each of the objects, a prediction of the future state related with each of the objects on the basis of the target value that is corrected by the correction, and a determination of whether or not the predicted future state related with each of the objects satisfies the constraint conditions are repeated ...

A METHOD AND APPARATUS FOR PREDICTING STEADY-STATE RESPONSE IN SLOW SENSOR REACTION

The present invention relates generally to a method and apparatus for predicting steady state response of a slow sensor reaction by utilising at least one batch of initial measured data for efficient data acquisition thereby saving time, energy and cost.

EXCAVATION CONTROL SYSTEM FOR HYDRAULIC SHOVEL

An excavation control system (200) is provided with the following: a global coordinate calculator (23); a prediction correction unit (261); a bucket-blade-end position data generation unit (282); and a design topographic data generation unit (283). The global coordinate calculator (23) generates revolving body orientation data (Q) that indicates the orientation of a revolving body (3). The prediction correction unit (261) predicts and corrects the revolving body orientation data (Q) on the basis of delay time (t) and revolution angle acceleration data (Dω) that indicates the revolution angle acceleration (ω) of the revolving body (3), thereby generating corrected revolving body orientation data (R). The bucket-blade-end position data generation unit (282) generates bucket-blade-end position data (S), that indicates the position of the bucket blade end (8a), on the basis of reference position data (P1), revolving body orientation data (Q), and corrected revolving body orientation data (R ...

METHOD FOR CONTROLLING AEROGENERATORS FOR PRODUCING ELECTRICAL ENERGY

A method for controlling an aerogenerator (1) for producing electrical energy of the type comprising an arrangement of aerodynamic elements (2) that rotate on a common shaft (3), sensors (4) for measuring at least the speed of the wind incident upon said elements (2), an alternator unit (5) associated with the rotation of the shaft (3) for generating electrical energy supplied to a use point (7) and/or to a battery (8) or for transmitting a mechanical torque to the shaft (3), and a control unit (6) associated with the sensor (4) and with the alternator (5) in order to control the alternator (5).

METHOD OF PREDICTING OPTICAL PROPERTIES AND PHYSICAL CHARACTERISTICS TO FORMULATE OPTIMUM COATING SYSTEM

Method of predicting optical properties and physical characteristics of coated paper or other sheet products for the purpose of formulating enhanced coating or sheet forming systems, and in particular to a method, which uses a diffusion approximation model derived from a radiative transfer theory employing various inputs of the properties and/or characteristics to predict coating or sheet system performance.

Control apparatus, control method, and engine control unit

A control apparatus, a control method, and an engine control unit are provided for controlling an output of a controlled object which has a relatively large response delay and/or dead time to rapidly and accurately converge to a target value. When the output of the controlled object is chosen to be that of an air/fuel ratio sensor in an internal combustion engine, the output of the air/fuel ratio sensor can be controlled to rapidly and accurately converge to a target value even in an extremely light load operation mode. The control apparatus comprises an ADSM controller for calculating a target air/fuel ratio in accordance with a predicted value of an output deviation based on a AL modulation algorithm, and a PRISM controller for calculating the target air/fuel ratio in accordance with the predicted value based on a sliding mode control algorithm. The control apparatus selects one of the target air/fuel ratios calculated by the two controllers to control the air/fuel ratio using the selected ...

Cascaded control of an average value of a process parameter to a desired value

A multi-tier controller directs operation of a system performing a process. The process has multiple process parameters (MPPs), at least one of the MPPs being a controllable process parameter (CTPP) and one of the MPPs being a targeted process parameter (TPP). The process also has a defined target limit (DTV) representing a first limit on an actual average value (MV) of the TPP over a defined time period of length TPL_AAV2. The AAV is computed based on actual values (AVs) of the TPP over the defined period. A first logical controller predicts future average values (FAVs) of the TPP over a first future time period (FFTP) having a length of at least TPL_AAV2 and extending from a current time T₀ to an future time T_AAV2, prior to which the TPP will move to steady state. The FAVs are predicted based on (i) the AAVs of the TPP at various times over a first prior time period (FPTP) having a length of at least TPL_AAV2 and extending from a prior ...

SUPPLY-DEMAND BALANCING METHOD AND SYSTEM FOR POWER MANAGEMENT IN SMART GRID

A Stackelberg game approach is used to describe a Demand-Response (DR) model for electricity trading between one utility company and multiple users, balancing supply and demand as well as smoothing an aggregated load in the power grid system. The interactions between the utility company and users are formulated into a 1-leader and N-follower Stackelberg game, where optimization problems are formed for each player to help select an optimal strategy. A pricing function is adopted for regulating real-time prices (RTP), and acts as a coordinator inducing users to join the game. An iterative algorithm is proposed to derive a Stackelberg equilibrium, through which optimal power generation and power demands are determined for the utility company and users, respectively.

System and method to predict optimized energy consumption

A system receives an energy demand response schedule, one or more user preferences, and one or more predicted environmental variables into a computer processor. The system generates an optimized energy schedule as a function of the demand response schedule, the user preferences, and the predicted environmental variables. The optimized energy schedule includes one or more of a set point temperature variation in one or more zones, an air handling unit set point temperature variation, a chilled water set point temperature variation, a carbon dioxide level set point variation, a pre-cooling time shift, a pre-cooling duration variation, and a load based optimized chiller schedule. The system transmits the optimized energy schedule to a building management server.

Method and Apparatus for Electrical Distribution Grid Control

According to one aspect of the teachings herein, a controller communicatively couples to and advantageously exploits a distributed control network of an industrial plant by, for example, using information received over the distributed control network to predict the value of one or more electrical parameters of an electrical distribution grid of the industrial plant, and to generate and transmit converter control commands based on the predicted value(s). These converter control commands target one or more converters located within the electrical distribution grid, each converter having an Active Front End or AFE that allows the reactive power consumption of the converter to be adjusted via the converter control commands.

SERVO CONTROL APPARATUS CONTROL METHOD

It is constructed so as to be able to follow without delay and flexibly cope with a change in a command of a host controller in the case of receiving a target command value at the present time from the host controller every certain period. In a servo control apparatus 2 for causing an output of a controlled object 3 to follow target commands received from a host controller 1 every certain period, predictive target commands to the next M steps are generated every each period using a history of the target commands and command follow-up control is performed by predictive and preview control or feedback gain switching control using the predictive target commands.

Method and apparatus for providing multivariable nonlinear control

A method and apparatus for training and optimizing a neural network for use in controlling multivariable nonlinear processes. The neural network can be used as a controller generating manipulated variables for directly controlling the process or as part of a controller structure generating predicted process outputs. The neural network is trained and optimized off-line with historical values of the process inputs, outputs, and their rates of change. The determination of the manipulated variables or the predicted process outputs are based on an optimum prediction time which represents the effective response time of the process output to the setpoint such that the greatest change to the process output occurs as a result of a small change made to its paired manipulated variable. ...

AUTOMATED VEHICLE CONTROL WITH TIME TO TAKE-OVER COMPENSATION

BEHAVIOR CONTROLLER, BEHAVIOR CONTROL METHOD, AND PROGRAM

PROBLEM TO BE SOLVED: To efficiently search a vast state space for generating an action sequence for achieving a goal. SOLUTION: A prediction part 131 always predictively learns a value taken by a sensor input at time t+1 from an action At and a sensor input St carried out at a time t by an autonomous agent and uses a function approximator based on statistical learning in learning. A goal generation part 132 gives a previously designed goal state matching a task to a planning part 133. The planning part 133 plans an action sequence from the current state to the goal state. When the plan to the goal can be generated, its sequence is carried out sequentially. When the plan succeeds, relation between the observed state and the selected action is learned by using the goal state as a fixed input. A control part 134 performs leaning using the plan and an environment by the planning part 133 as a teacher for controlling an action of an autonomous agent and learns input-output relation of the action ...

КАСКАДНОЕ РЕГУЛИРОВАНИЕ ДЛЯ ЗАДАНИЯ ТРЕБУЕМОГО СРЕДНЕГО ЗНАЧЕНИЯ ТЕХНОЛОГИЧЕСКОГО ПАРАМЕТРА

Изобретение относится к многоуровневому контроллеру, который управляет работой системы, выполняющей технологический процесс. Техническим результатом является повышение эффективности управления работой системы. Процесс имеет несколько технологических параметров (МРР): один из МРР является управляемым технологическим параметром (СТРР) и один из МРР является целевым технологическим параметром (ТРР); и заданный целевой предел (DTV), представляющий первый предел фактического среднего значения (AAV) ТРР за заданный период времени продолжительностью TPLAAV2. AAV вычисляется на основе фактических значений (AV) ТРР за заданный период. Первый логический контроллер прогнозирует будущие средние значения (FAV) ТРР за первый будущий период времени (FFTP), имеющий продолжительность TPLAAV2 и идущий от текущего момента времени Т0 до будущего момента времени ТAАV2, до которого ТРР перейдет в установившийся режим. FAV прогнозируются на основе (i) AAV TTP в различные моменты времени за первый предшествующий ...

Verfahren und Anordnung zum Entwurf eines technischen Systems

Die Erfindung betrifft ein Verfahren zum Entwurf eines technischen Systems, bei dem das technische System durch eine vorgegebene Menge von Zielfunktionen, die von Parametern abhängen, modelliert wird. Dabei wird jede einzelne Zielfunktion mit einem Gewichtsfaktor gewichtet. Das Verfahren löst ein Gleichungssystem, umfassend die Parameter und die Gewichtungsfaktoren als Variablen in einem Variablenraum, wobei Lösungen des Gleichungssystems Arbeitspunkte eines Lösungsraums im Variablenraum bilden. Bei dem erfindungsgemäßen Verfahren werden die Arbeitspunkte mittels eines Prädiktor-Korrektor-Verfahrens bestimmt, bei dem ausgehend von einem ersten Arbeitspunkt ein Prädiktor, der mittels einer stochastischen Größe erzeugt wird, im Variablenraum bestimmt wird und anschließend in einem Korretorschritt ein zweiter Arbeitspunkt ermittelt wird. Die ermittelten Arbeitspunkte werden dabei zum Entwurf des technischen Systems eingesetzt. Bei dem Entwurf des technischen Systems kann es sich um einen Neuentwurf ...

FALL-BASIERTES DEDUKTIVES SYSTEM, VERFAHREN UND GERÄT FÜR SENSOR-PREDIKTION IN EINEM TECHNISCHEN PROZESS, INSBESONDERE IN EINEM ZEMENTOFEN

Controller for use in several control systems, has automatic control loops linked by multi-value control software for accessing parameters of control systems and for independently controlling control systems

The controller has automatic control loops that are linked by multi-value control software for accessing the parameters of several control systems, and for independently controlling the control systems. The automatic control loops are formed using a given function and the upward gradient characteristics or indicator of the control variables from the given function.

Control system, obtains gradient indicator from function, where control value gradient assumes non efficiency of absolute value of difference from offset and initial value and assumes another absolute value of control variable difference

The system obtains a gradient indicator from a predetermined function. The limitation of the gradient indicator serves directly in connection with its computation. A control value gradient assumes a non efficiency of an absolute value of the difference from offset and an initial value and assumes another absolute value of a reference control variable difference. A direction factor is multiplied with a sign factor.

Tire uniformity prediction using curve fitting

An improved microgrid control apparatus, method and system

A microgrid controller 70 monitors the energy consumption and/or generation of equipment within a microgrid, generates data representative of consumption/generation in a prior time period and nominates a time and length of a future time period. The energy data and time period data are transferred between the controller 70 and another microgrid controller. The controller includes a processor that selects a source or sink to be used during a future time period based on its own energy/time period data and that of another controller. The future time period may be determined using nomination data, which may comprise user instructions, data representing rate of change of energy generation/consumption in a prior time period and/or data representing equipment energy prediction data. The controller may control the operation of generators and loads based on the transferred data by connecting or disconnecting equipment and varying power drawn. The energy data may include numbers representing a value ...

An improved microgrid control apparatus, method and system

Dynamic prediction for process control

MACHINE LEARNING OF PHYSICAL CONDITIONS BASED ON ABSTRACT RELATIONS AND SPARSE LABELS

A method for determining specific conditions occurring on industrial equipment based upon received signal data from sensors attached to the industrial equipment is provided. Using a server computer system, signal data is received and aggregated into feature vectors. Feature vectors represent a set of signal data over a particular range of time. The feature vectors are clustered into subsets of feature vectors based upon attributes the feature vectors. One or more sample episodes are received, where a sample episode includes sample feature vectors and specific classification labels assigned to the sample feature vectors. A signal data model is created that includes the associated feature vectors, clusters, and assigned classification labels. The signal data model is used to assign classification labels to newly received signal data using the mapping information for the existing feature vectors, existing clusters and associated classification labels to determine the specific conditions occurring ...

MACHINE LEARNING OF PHYSICAL CONDITIONS BASED ON ABSTRACT RELATIONS AND SPARSE LABELS

A method for determining specific conditions occurring on industrial equipment based upon received signal data from sensors attached to the industrial equipment is provided. Using a server computer system, signal data is received and aggregated into feature vectors. Feature vectors represent a set of signal data over a particular range of time. The feature vectors are clustered into subsets of feature vectors based upon attributes the feature vectors. One or more sample episodes are received, where a sample episode includes sample feature vectors and specific classification labels assigned to the sample feature vectors. A signal data model is created that includes the associated feature vectors, clusters, and assigned classification labels. The signal data model is used to assign classification labels to newly received signal data using the mapping information for the existing feature vectors, existing clusters and associated classification labels to determine the specific conditions occurring ...

OPTIMIZING AND CONTROLLING THE ENERGY CONSUMPTION OF A BUILDING

Described herein are methods and systems, including computer program products, for optimizing and controlling the energy consumption of a building. A first computing device generates a set of thermal response coefficients for the building based on energy characteristics of the building and weather data associated with the location of the building. The first computing device predicts an energy response of the building based on the set of thermal response coefficients and forecasted weather associated with the location of the building. The first computing device selects minimal energy requirements of the building based on an energy consumption cost associated with the building. The first computing device determines one or more temperature set points for the building based on the energy response and the minimal energy requirements. The first computing device transmits the one or more temperature set points to a thermostat of the building.

MULTIVARIABLE PROCESS CONTROL METHOD AND APPARATUS

On-line control of a process is achieved by feedforward computations of manipulated variables setpoints (SP) modified during each of frequent optimization cycles by feedback trim (84) determined by actual versus predicted effects of setpoints changes on the process controlled variables. Process, economic, contractual and equipment parameter values are continuously polled and collected and used to compute the optimal setpoints for the manipulated variables before the feedback trim (84) is applied. Drift factors (87) are added to the feedback trim (84) to provide on-line calibration of key measuring instruments. Drifts in process performance (87) are updated on-line periodically through self-running routines (72, 85) computed as calibration factors for predictor (81) and control (71) equations based on rigorous process simulations and actual plant performance.

A METHOD OF PROCESS CONTROLLER OPTIMIZATION IN A MULTIVARIABLE PREDICTIVE CONTROLLER

In a process control system, having a controller for providing robust control of a process, the controller utilizes a predetermined range control procedure, the results being a control solution. The process has at least one manipulated variable and at least one controlled variable. A method of providing dynamic optimization comprises the steps of calculating an optimized set of steady state values of the manipulated variables and the controlled variables. An augmented range control procedure is created to harmonize the set of steady state values with the control solution. The augmented range control procedure is solved, the manipulated variables generated thereby being compatible with the set of steady state values and with the control solution. The process is controlled in accordance with the manipulated variables generated by the augmented range control procedure, thereby providing optimal control of the process.

Coordination in multilayer process control and optimization schemes

INFERENTIAL SENSORS DEVELOPED USING THREE-DIMENSIONAL PARETO-FRONT GENETIC PROGRAMMING

A predictive algorithm for predictive at least one output variable based on a plurality of input variables is developed using a genetic programming technique that evolves a population of candidate algorithms through multiple generations. Within each generation, the candidate algorithms are evaluated based on three fitness criteria: (i) an accuracy criterion that evaluates each candidate algorithm's ability to predict historical measurements of the at least one output variable based on corresponding historical measurements of the input variables; (ii) a complexity criterion that evaluates each candidate algorithm's complexity; and (iii) a smoothness criterion that evaluates each candidate algorithm's nonlinearity. The predictive algorithm may be implemented in an inferential sensor that is used to monitor a physical, chemical, or biological process, such as an industrial process in an industrial plant.

Receding horizon based adaptive control having means for minimizing operating costs

Disclosed is an adaptive and predictive controller having self tuning capabilities. The receding horizon window and sample interval are determined by the tunning mechanism automatically, based on the relationship between the controlled and manipulated variables. The interval and window may be set by the user as well. Constraints on the manipulated and controlled variables at the end of the horizon window are accommodated automatically. In addition to providing servo regulatory control the invention teaches simultaneous minimization of operating costs.

Gas liquefaction process control system

Universal method for pre-calculating parameters of industrial processes

The invention relates to a method for pre-calculating the parameters of industrial processes. According to said method, an admissible process input variable vector is determined with definition ranges allocated to each variable and a process output variable vector is determined with the pre-calculable process parameters. Known information on the process is stored in a data bank and ranges of validity for the process input variables are allocated to said information. For each process input vector inputted from an admissible definition range provided with valid information, exactly one process output vector is determined according to the information valid therefor.

Adaptive control methods for buildings

A method is provided for controlling a first switch terminal or equivalent of a building occupied by one or more building occupants. A plurality of switch terminal or equivalent parameters are provided relative to the building. A first computer system is coupled to the first switch terminal or equivalent of the building at a first location of the building. The first computer system runs on at least one platform. A first plurality of sensors is coupled to the first switch terminal or equivalent and the first computer system. At least a portion of the sensors are used to provide signal data to the first computer system. From the first computer system a command or data output is produced that relates to at least one of: a command output for a local control system, a command output for a different system, a data output for a different system, a command output for a non-local device or a data output that is a non-local device. Each of an output includes learned data from that is based on a machine ...

POWER COORDINATION CONTROL SYSTEM, POWER COORDINATION CONTROL METHOD, AND NON-TRANSITORY STORAGE MEDIUM

Power coordination control systems (10a-10c) are provided with superimposed signal generation units (11a-11c), transmission units (12a-12c), receiving units (13a-13c) and connection relation estimation units (14a-14c). At the location of a utility consumer A (20), the superimposed signal generation unit (11a) generates a superimposed signal by superimposing a prescribed signal on a voltage supplied from a system (50). The transmission unit (12a) transmits the superimposed signal generated in the superimposed signal generation unit (11a) from the utility consumer A (20) to utility consumers B (30) and C (40). The receiving unit (13b) receives the superimposed signal at the location of the utility consumer B (30). The connection relation estimation units (14a-14c) estimate the connection relation between the utility consumer A (20) and the utility consumer B (30) on the basis of the receiving status of the superimposed signal and/or the received information received by the receiving units ...

AIR CONDITIONING CONTROL SYSTEM AND AIR CONDITIONING CONTROL METHOD

A disclosed air conditioning control system includes: a flow path through which cooling air discharged from an exhaust surface of an electronic apparatus is returned to an intake surface thereof, a damper provided in the flow path, a temperature measuring unit for measuring the real temperature of the cooling air, a humidity measuring unit for measuring the real humidity of the cooling air, a target value changing unit for changing target temperature and humidity in accordance with the real temperature and humidity, and a controlling unit for predicting future predicted values of the real temperature and humidity, and controlling the opening extent of the damper such that the predicted temperature and humidity become close to the target temperature and humidity, respectively. The target value changing unit sets the target temperature and humidity such that the real temperature and humidity are raised and lowered in the opposite directions.

Method and system for integrated analysis

A system and method of analysis, including, but not limited to: receiving raw data related to at least one project; receiving user preferences in at least one workflow, wherein each step in the a workflow constitutes a single instance of a component of a workflow such that the state of a unique component is always the same if the same component is comprised in other workflows; determining metrics related to the at least one project; analyzing the data & metrics to identify patterns; drawing conclusions from the data, metrics and patterns; and generating at least one report that presents the metrics, patterns and conclusions.

Energy-Optimal Control Decisions for Systems

Methods, systems, and apparatuses are provided for controlling an environmental maintenance system that includes a plurality of sensors and a plurality of actuators. The operation levels of the actuators can be determined by optimizing a penalty function. As part of the penalty function, the sensor values can be compared to reference values. The optimized values of the operation levels can account for energy use of actuators at various operation levels and predicted differences of the sensor values relative to the reference values at various operation levels. The predicted difference can be determined using a transfer model. An accuracy of the transfer model can be determined by comparing predicted values to measured values. This accuracy can be used in determining new operational levels from an output of the transfer model (e.g., attenuating the output of the transfer model based on the accuracy).

Autonomous biologically based learning tool

An autonomous biologically based learning tool system and a method that the tool system employs for learning and analysis are provided. The autonomous biologically based learning tool system includes (a) one or more tool systems that perform a set of specific tasks or processes and generate assets and data related to the assets that characterize the various processes and associated tool performance; (b) an interaction manager that receives and formats the data, and (c) an autonomous learning system based on biological principles of learning. The autonomous learning system comprises a memory platform and a processing platform that communicate through a network. Both the memory platform and the processing platform include functional components and memories that can be defined recursively. Knowledge generated and accumulated in the autonomous learning system(s) can be cast into semantic networks that can be employed for learning and driving tool goals based on context.

Biologically based chamber matching

The subject disclosure relates to automatically learning relationships among a plurality of manufacturing tool parameters as applied to arbitrary semiconductor manufacturing tools and a graphical user interface that is supported, at least in part, by an autonomous learning system. The graphical user interface can create one or more matrixes based on received data and can further generate additional matrices by transforming the one or more matrixes. A series of windows can be output, wherein the series of windows, provide performance analysis that comprises a matching between a focus chamber and a reference chamber. In an aspect, the focus chamber and the reference chamber can be different chambers. In another aspect, the focus chamber and the reference chamber can be the same chamber, which provides analysis of the deterioration in performance of the same chamber over time.

Method and circuit configuration for determining position minus time

A circuit configuration for a data processing system for predicting a coordinate for at least one operation to be carried out is provided, the prediction being connected to at least one input signal and being a function of a predefined first time value and at least one predefined first value which represents another physical variable. Upon each change of the at least one input signal, a second time value is calculated in each case from the first value, and to subtract the first time value from the second time value to form a third time value, and/or to calculate a second value from the first time value, and to subtract the first value from the second value to form a third value, in order to determine from the third time value and/or the third value a state in which the at least one operation is to be carried out.

Motor control apparatus

A motor control apparatus that controls rotation of a rotor of an electric motor powered from an electric power source includes a learning portion that executes an initial drive learning process, and a controller that executes a normal drive operation to sequentially change an exciting phase of the electric motor based on a count value of a counter which is corrected by a correcting portion such that the rotor is rotated to a target position after an initial drive operation is finished. The learning portion re-executes the initial drive learning process after a predetermined condition is satisfied, when the initial drive learning process is failed.

Method for closed-loop controlling a laser processing operation and laser material processing head using the same

The present invention relates to a method for closed-loop controlling a processing operation of a workpiece, comprising the steps of: (a) recording a pixel image at an initial time point of an interaction zone by means of a camera, wherein the workpiece is processed using an actuator having an initial actuator value; (b) converting the pixel image into a pixel vector; (c) representing the pixel vector by a sum of predetermined pixel mappings each multiplied by a corresponding feature value; (d) classifying the set of feature values on the basis of learned feature values into at least two classes of a group of classes comprising a first class of a too high actuator value, a second class of a sufficient actuator value and a third class of a too low actuator value at the initial time point; (e) performing a control step for adapting the actuator value by minimizing the error e t between a quality indicator y e and a desired value; and (f) repeating the steps (a) to (e) for further time points to perform a closed-loop controlled processing operation.

PROCESS CONTROL SYSTEMS AND METHODS HAVING LEARNING FEATURES

A system for operating a process includes a processing circuit that uses a self-optimizing control strategy to learn a steady-state relationship between an input and an output. The processing circuit is configured to switch from using the self-optimizing control strategy to using a different control strategy that operates based on the learned steady-state relationship. 1. A system for operating a process , comprising:a processing circuit that uses a self-optimizing control strategy to learn a steady state relationship between a manipulated variable and an output variable;wherein the processing circuit is configured to automatically switch from using the self-optimizing control strategy to using a second control strategy that operates using the learned steady state relationship.2. The system of claim 1 , wherein the second control strategy is an open loop control strategy that conducts open loop control based on the learned steady-state relationship.3. The system of claim 1 , wherein the second control strategy includes a feedback loop that operates based on the learned steady-state relationship.4. The system of claim 1 , wherein the processing circuit is configured to operate in the second control strategy normally and the self-optimizing control strategy periodically.5. The system of claim 1 , wherein the processing circuit is configured to operate the process according to the self-optimizing control strategy during a start-up state of the process.6. The system of claim 5 , wherein the processing circuit is configured to detect when a steady state has been reached after the start-up of the process.7. The system of claim 6 , wherein learning a steady-state relationship between the input and output comprises seeking a manipulated variable estimated to minimize energy consumption.8. The system of claim 7 , wherein the self-optimizing control strategy is an extremum seeking control strategy.9. The system of claim 1 , wherein the self-optimizing control strategy is an ...

Computational load distribution in a climate control system having plural sensing microsystems

Systems, methods, and related computer program products for controlling one or more HVAC systems using a distributed arrangement of wirelessly connected sensing microsystems are described. A plurality of wirelessly communicating sensing microsystems is provided, each sensing microsystem including a temperature sensor and a processor, at least one of the sensing microsystems being coupled to an HVAC unit for control thereof. The plurality of sensing microsystems is configured to jointly carry out at least one shared computational task associated with control of the HVAC unit. Each sensing microsystem includes a power management circuit configured to determine an amount of electrical power available for dedication to the at least one shared computational task. The at least one shared computational task is apportioned among respective ones of the plurality of sensing microsystems according to the amount of electrical power determined to be available for dedication thereto at each respective sensing microsystem.

Systems and methods for autoconfiguration of pattern-recognition controlled myoelectric prostheses

Embodiments of the invention provide for a prosthesis guided training system that includes a plurality of sensors for detecting electromyographic activity. A computing device, which can include a processor and memory, can extract data from the electromyographic activity. A real-time pattern recognition control algorithm and an autoconfiguring pattern recognition training algorithm can be stored in the memory. The computing device can determine movement of a prosthesis based on the execution of the real-time pattern recognition control algorithm. The computing device can also alter operational parameters of the real-time pattern recognition control algorithm based on execution of the autoconfiguring pattern recognition training algorithm.

Method and apparatus for delivering power using external data

A control system for an energy storage system located behind a utility meter uses a unique, feedback-based, communication and control method to reliably and efficiently maximize economic return of the energy storage system. Operating parameters for the energy storage system are calculated at an external, centralized data center, and are selected to prevent electrical power demand of an electric load location from exceeding a specified set-point by discharging energy storage devices, such as DC batteries, through a bidirectional energy converter during peak demand events. The control system can operate autonomously in the case of a communications failure.

Adaptive and automatic determination of system parameters

A method of automatically determining process parameters for processing equipment includes processing at least one first substrate in the processing equipment at a first time; and processing at least one second substrate in the processing equipment at a second time. The method includes collecting data on process monitors for the at least one first substrate; and the at least one second substrate. The method includes receiving the data by a multiple-input-multiple-output (MIMO) optimization system. The method includes revising a sensitivity matrix, by a MIMO optimizer, using the data and an adaptive-learning algorithm, wherein the adaptive-learning algorithm revises the sensitivity matrix based on a learning parameter which is related to a rate of change of the processing equipment over time. The method includes determining a set of process parameters for the processing equipment by the MIMO optimizer, wherein the MIMO optimizer uses the revised sensitivity matrix to determine the process parameters.

ELECTRIC/THERMAL ENERGY STORAGE SCHEDULE OPTIMIZING DEVICE, OPTIMIZING METHOD AND OPTIMIZING PROGRAM

A device includes a setting unit setting a control target value for setting an activation, an operation, and a deactivation at a next day for control-target devices including an energy supplying device, an energy consuming device consuming energy, and an energy storage device storing energy, a predicting unit that sets a predicted value of the consumed energy of the energy consuming device at the next day based on a comparison between the control setting value set by the setting unit and a past control setting value, a start-stop optimizing unit that creates a start-stop schedule obtained by optimizing the start-stop schedule of the control-target device at the next day by an evaluation index, and a status-quantity optimizing unit that creates an electric/thermal energy storing schedule obtained by optimizing the status quantity of the control-target device to be activated by a predetermined evaluation index. 1. An electric/thermal energy storage schedule optimizing device comprising:a setting unit that sets a control setting value for setting an activation, an operation, and a deactivation during a future predetermined time period for at least one of control-target devices that are an energy supplying device including a device which changes an energy supply level depending on a weather condition, an energy consuming device which consumes energy, and an energy storage device which stores energy;a predicting unit that sets a predicted value of consumed energy of the energy consuming device or supplying energy of the energy supplying device during the future predetermined time period based on a comparison between the control setting value set by the setting unit and a past control setting value;a start-stop optimizing unit that creates a start-stop schedule obtained by optimizing a start-stop schedule of the control-target device during the predetermined time period based on the predicted value and a characteristic of the control-target device in view of a ...

AVAILABILITY PREDICTION APPARATUS FOR ELECTRIC POWER STORAGE DEVICE

An availability prediction apparatus includes an access section that accesses a storage section and a prediction section. The storage section stores availability specified periods occurred before a present time associated with respective frequencies of the availability specified periods, and the access section acquires the availability specified periods from the storage section. The prediction section predicts at least one target availability specified period within a prediction term, which begins at the present time and ends at a time later than the present time by a predetermined term. The prediction section includes a correlating section that correlates the availability specified periods with candidate periods included in the prediction term, and a selection section that specifies and selects one of the candidate periods having a highest occurrence probability as the target availability specified period. 1. An availability prediction apparatus for an electric power storage device of an electric power system that executes an electric power transfer control using the electric power storage device , the availability prediction apparatus comprising:an access section that accesses a storage section storing a plurality of availability specified periods occurred before a present time associated with respective frequencies of the availability specified periods and acquires the availability specified periods and the respective frequencies of the availability specified periods from the storage section, the availability specified periods being available periods or unavailable periods, wherein, during the available periods, the electric power storage device is available for the electric power transfer control, and during the unavailable periods, the electric power storage device is unavailable for the electric power transfer control; anda prediction section that executes a prediction process in order to predict at least one target availability specified period to be occurred ...

CALCULATION DEVICE, CALCULATION METHOD, AND STORAGE MEDIUM

A calculation device, a calculation method, and a storage medium are provided. The present invention is provided with: a first calculation unit which, with respect to input data, performs calculations relating to predetermined processing by using a first model in which a corresponding relationship between input data and output data changes by performing machine learning that uses learning data, and outputs a first output; a second calculation unit which, with respect to input data, performs calculations relating to predetermined processing using a second model for which the correspondence relationship between input data and output data is fixed, and outputs a second output; and a comparison unit which, on the basis of a comparison result obtained by comparing the first output and the second output with a prescribed determination standard, outputs the first output, the second output, or a third output that is a combination of the first and second outputs. 1. A calculation device , comprising:a first calculation unit which performs, on input data, calculation relating to a predetermined processing using a first model in which a corresponding relationship between input data and output data is changed by performing machine learning using a learning data, and outputs a first output;a second calculation unit which performs, on the input data, calculation relating to the process using a second model in which a corresponding relationship between input data and output data is fixed, and outputs a second output; anda comparison unit which outputs the first output, the second output, or a third output obtained by combining the first output and the second output based on a result obtained by comparing the first output and the second output using a predetermined determination criterion.2. The calculation device according to claim 1 , further comprisinga learning unit which learns parameters of the first model and sets the learned parameters in the first model.3. The calculation ...

ENVIRONMENT FACTOR CONTROL DEVICE AND TRAINING METHOD THEREOF

Disclosed is a non-transitory computer readable medium storing a computer program, wherein the computer program includes instructions to perform following steps for data processing when the computer program is executed by one or more processors, the steps including: recognizing at least one continuous section from each raw data subset; determining at least one serialization point, based on a start point and an end point of each of the at least one continuous section for each of the raw data subset; and generating a training data set by generating serialized training data, based on the at least one serialization point. 1. A non-transitory computer readable medium storing a computer program , wherein the computer program includes instructions to perform following steps for data processing when the computer program is executed by one or more processors , the steps comprising:generating at least one raw data subset based on a set of raw data;determining at least one continuous section for each of the at least one raw data subset; andgenerating a first training data set by generating a serialized training data, based on each of the at least one continuous section.2. The non-transitory computer readable medium according to claim 1 , wherein the generating at least one raw data subset based on a set of raw data includes:recognizing at least one raw data which is a vector having at least one type of an environmental factor and time as elements from the set of raw data; andgenerating the at least one raw data subset comprising the at least one raw data recognized.3. The non-transitory computer readable medium according to claim 1 , wherein the at least one raw data subset includes at least one raw data which is continuously expressed in a coordinate space without disconnection.4. The non-transitory computer readable medium according to claim 1 , wherein the generating a first training data set by generating a serialized training data claim 1 , based on each of the at least ...

VEHICLE INTERSECTION OPERATION

A computer includes a processor and a memory, the memory storing instructions executable by the processor to collect a plurality of images of one or more targets at an intersection, input the images to a machine learning program to determine a number of the targets to which a host vehicle is predicted to yield at the intersection based on time differences between the plurality of images, and transmit a message indicating the number of the targets. 1. A system , comprising a computer including a processor and a memory , the memory storing instructions executable by the processor to:collect a plurality of images of one or more targets at an intersection;input the images to a machine learning program to determine a number of the targets to which a host vehicle is predicted to yield at the intersection based on time differences between the plurality of images; andtransmit a message indicating the number of the targets.2. The system of claim 1 , wherein the instructions further include instructions to actuate a brake of the host vehicle to yield to the targets at the intersection.3. The system of claim 1 , wherein the instructions further include instructions to claim 1 , upon yielding to a first of the targets claim 1 , transmit a message indicating a new number of the targets to which the host vehicle is predicted to yield at the intersection.4. The system of claim 1 , wherein the instructions further include instructions to apply the machine learning program to predict an order of the targets to which the host vehicle is predicted to yield at the intersection.5. The system of claim 4 , wherein the instructions further include instructions to predict the order based on respective differences of a distance between each target and a respective stopping point at the intersection.6. The system of claim 5 , wherein the stopping point is one of a traffic sign and a road marking.7. The system of claim 4 , wherein the instructions further include instructions to predict the ...

REMOTE OPERATION SYSTEM FOR WORKING MACHINE

A remote operation system for a working machine includes a control device enabling an operator wearing a wearable display to grasp the surrounding situation of himself/herself. The control device includes an operation intention judgment section judging the presence/absence of an operator's operation intention to a remote operation lever based on the contents of acquired judgment information, and a display image switching section. With judgment of presence of the operation intention, the display image switching section makes a working area image taken by a working area image taking camera be displayed in a particular display area of the wearable display. With judgment of absence of the operation intention, the display image switching section stops the display of the working area image in the at least a part of the particular display area and switches it to a surrounding visual-recognition allowing area allowing the operator to visually recognize the surroundings. 1. A remote operation system for remotely operating a working machine , the remote operation system comprising:a remote operation lever that is disposed at a position distant from the working machine and allows an operation to be applied to the remote operation lever by an operator of the working machine while being held by the operator;at least one judgment information acquisition device capable of acquiring judgment information for judging presence or absence of an operation intention that is an intention of the operator to apply an operation to the remote operation lever;a working area image taking camera that is disposed on the working machine and capable of taking a working area image that is an image of surroundings of the working machine;a wearable display capable of displaying an image to the operator while being worn on the operator, the wearable display having a particular display area in which the working area image can be displayed; anda control device that causes the wearable display to display ...

Spectral Lighting Modeling and Control

Spectral irradiance distributions are calculated within a virtual environment based on arbitrary light source spectral power distributions. Architectural, horticultural and aquacultural lighting control systems use the calculated results to control both the intensity and spectral power distribution of the electric light sources. Energy consumption may be minimized while maintaining optimal occupant visual comfort and plant health. 1. A method of predicting a spectral irradiance distribution for an arbitrary position and arbitrary view direction in a virtual environment , comprising the steps of:calculating, by a processor, a direct spectral irradiance for said position and direction due to one or more light sources illuminating the virtual environment;calculating, by the processor, an indirect spectral irradiance for said position and direction due to reflections from one or more surfaces in the virtual environment, said indirect spectral irradiance calculated as a per-wavelength multiple of the direct spectral irradiance; andsumming, by the processor, the direct spectral irradiance and the indirect spectral irradiance to result in the spectral irradiance distribution.2. The method of claim 1 , wherein calculating the indirect spectral irradiance comprises:assigning RGB triplets to one or more surfaces in the virtual environment based on a reference illuminant; and calculating, by the processor, an indirect tristimulus irradiance for said position and direction due to reflections from one or more surfaces in the virtual environment;', 'reconstructing, by the processor, a physically plausible relative spectral power distribution from the indirect tristimulus irradiance;', 'multiplying, by the processor, said relative spectral power distribution by a spectral power distribution of the light source and the reference illuminant on a per-wavelength basis, to result in a spectral power distribution; and', 'scaling, by the processor, the spectral power distribution ...

AUTOMATED CONTROL-SCHEDULE ACQUISITION WITHIN AN INTELLIGENT CONTROLLER

The current application is directed to intelligent controllers that initially aggressively learn, and then continue, in a steady-state mode, to monitor, learn, and modify one or more control schedules that specify a desired operational behavior of a device, machine, system, or organization controlled by the intelligent controller. An intelligent controller generally acquires one or more initial control schedules through schedule-creation and schedule-modification interfaces or by accessing a default control schedule stored locally or remotely in a memory or mass-storage device. The intelligent controller then proceeds to learn, over time, a desired operational behavior for the device, machine, system, or organization controlled by the intelligent controller based on immediate-control inputs, schedule-modification inputs, and previous and current control schedules, encoding the desired operational behavior in one or more control schedules and/or sub-schedules. 1a memory;a control schedule stored in the memory;a schedule interface;a control interface; and receive immediate-control inputs through the control interface during a monitoring period and record the received immediate-control inputs in memory;', 'receive schedule changes through the schedule interface during the monitoring period and record received schedule changes of at least one type in the memory;', 'generate an updated monitoring-period schedule, after the monitoring period, based on the recorded immediate-control inputs, recorded schedule changes, and the control schedule;', 'substitute the updated monitoring-period schedule for a portion of the control schedule corresponding to the monitoring period; and', 'propagate the updated monitoring-period schedule to additional time periods within the control schedule., 'instructions stored within the memory that, when executed by the processor,'}. An intelligent controller comprising: a processor; This application is a continuation of U.S. patent application ...

AUTONOMOUS DRONE PLAY AND DIRECTIONAL ALIGNMENT

Embodiments provide for autonomous drone play and directional alignment by in response to receiving a command for a remotely controlled device to perform a behavior, monitoring a first series of actions performed by the remotely controlled device that comprise the behavior; receiving feedback related to how the remotely controlled device performs the behavior, wherein the feedback is received from at least one of a user, a second device, and environmental sensors; updating, according to the feedback, a machine learning model used by the remotely controlled device to produce a second, different series of actions to perform the behavior; and in response to receiving a subsequent command to perform the behavior, instructing the remotely controlled device to perform the second series of actions. 1. A method , comprising:in response to receiving a command for a remotely controlled device to perform a behavior, monitoring a first series of actions performed by the remotely controlled device that comprise the behavior;receiving feedback related to how the remotely controlled device performs the behavior, wherein the feedback is received from at least one of a user, a second device, and environmental sensors;updating, according to the feedback, a machine learning model used by the remotely controlled device to produce a second, different series of actions to perform the behavior; andin response to receiving a subsequent command to perform the behavior, instructing the remotely controlled device to perform the second series of actions.2. The method of claim 1 , wherein the command specifies a series of user-defined actions that comprise the first series of action to teach the behavior to the machine learning model claim 1 , wherein receiving the feedback refines the behavior in the machine learning model.3. The method of claim 2 , wherein the feedback refines behavior in the machine learning model by one of:adding an additional action to the first series of actions;removing ...

CLOTHES TREATING APPARATUS AND METHOD FOR OPERATING THE CLOTHES TREATING APPARATUS

A clothes treating apparatus which controls a temperature of clothes and an operating time by executing an artificial intelligence (AI) algorithm and/or a machine learning algorithm in a 5G environment connected for Internet of Things and an operating method of the clothes treating apparatus are provided. The clothes treating apparatus includes a communicator, a controller, a memory, a storage space, a temperature sensor, a temperature adjuster, and a fan. The communicator collects weather information and operation information of at least one connected device. Further, the communicator collects activity information or biometric information of the user from a portable terminal, a wearable device, or a vehicle. A user's preferred clothing temperature is derived by using clustering, deep learning, and reinforcement learning of the collected information, and the temperature of the clothes is adjusted based on the derived target temperature. 1. A clothes treating apparatus , comprising: a storage space to store clothes;', 'an intake port configured to introduce air into the storage space;', 'an exhaust port configured to discharge the air from the storage space;', 'a fan configured to circulate the air in the storage space;', 'at least one temperature sensor located at the main body;', 'a temperature adjustor located between the intake port and the exhaust port, the temperature adjustor configured to perform heating or cooling:, 'a main body including 'a communicator configured to collect weather information and operation information of at least one connected device; and', 'a door coupled to the main body so as to open or close the storage space;'} analyze the weather information and the operation information of the at least one connected device collected by the communicator to derive a target temperature; and', 'control a temperature of the storage space to be the derived target temperature by controlling operations of the temperature adjustor and the fan., 'a ...

MODEL FIDELITY MONITORING AND REGENERATION FOR MANUFACTURING PROCESS DECISION SUPPORT

Techniques for model fidelity monitoring and regeneration for manufacturing process decision support are described herein. Aspects of the invention include determining that an output of a regression model corresponding to a current time period of decision support for a manufacturing process is not within a predefined range of a historical process dataset, wherein the regression model was constructed based on the historical process dataset, and performing an accuracy and fidelity analysis on the regression model based on process data from the manufacturing process corresponding to a previous time period. Based on a result of the accuracy and fidelity analysis being below a threshold, a mismatch of the regression model as compared to the manufacturing process is determined. Based on determining the mismatch, a temporary regression model corresponding to the manufacturing process is generated, and decision support for the manufacturing process is performed based on the temporary regression model. 1. A computer-implemented method comprising:determining, by a processor, that an output of a regression model corresponding to a current time period of decision support for a manufacturing process is not within a predefined range of a historical process dataset from the manufacturing process, wherein the regression model was constructed based on the historical process dataset;based on determining that the output of the regression model corresponding to the current time period of decision support for the manufacturing process is not within the predefined range of the historical process dataset, performing an accuracy and fidelity analysis on the regression model based on process data from the manufacturing process corresponding to a previous time period;based on a result of the accuracy and fidelity analysis being below a threshold, determining a mismatch of the regression model as compared to the manufacturing process;based on determining the mismatch, generating a temporary ...

Control Apparatus, Device, Method and Computer Program for Determining a Device-Specific Supply Voltage for a Semiconductor Device

Examples relate to control apparatus, a control device, a method and a computer program for determining a device-specific supply voltage for a semiconductor device, and to a corresponding semiconductor device and corresponding systems. The control apparatus is configured to obtain measurement data of measurement circuitry of the semiconductor device, the measurement data being related to a progress of aging of the semiconductor device. The control apparatus is configured to determine the device-specific supply voltage of the semiconductor device based on the measurement data. The control apparatus is configured to provide information on the device-specific supply voltage for a supply voltage control apparatus. 1202002426. A control apparatus () for determining a device-specific supply voltage for a semiconductor device () , the control apparatus comprising processing circuitry () and storage circuitry () , wherein the control apparatus is configured to:Obtain measurement data of measurement circuitry of the semiconductor device, the measurement data being related to a progress of aging of the semiconductor device;Determine the device-specific supply voltage of the semiconductor device based on the measurement data; and{'b': '205', 'Provide information on the device-specific supply voltage for a supply voltage control apparatus ().'}2. The control apparatus according to claim 1 , wherein the device-specific supply voltage is based on the progress of aging of the semiconductor device claim 1 , with the progress of aging being based on an individual aging process of the semiconductor device in the field.3. The control apparatus according to claim 1 , wherein the control apparatus is configured to increase the device-specific supply voltage as the aging of the semiconductor device progresses.4. The control apparatus according to claim 1 , wherein the progress of aging of the semiconductor device is based on a utilization of the semiconductor device claim 1 , with the ...

COMBINED METHOD FOR DETECTING ANOMALIES IN A WATER DISTRIBUTION SYSTEM

A method for the detection of anomalies in a networked water distribution system is provided. It improves detection methods based on an iterative modification of control variables of the network, by determining a reduced set of entities of the water distribution network on which control variables should be iteratively modifier. The invention increases the computing costs, and the reliability of such methods of detecting anomalies in a water distribution system. 1. A method for detecting anomalies in a water distribution system composed of a network of nodes , said method comprising:parametrizing a hydraulic model of the water distribution system with a set of values of control variables comprising the network and its output at the nodes;using sensors on the network to acquire observations of a subset of state variables at first time references;identifying at least one target entity where to change the values of control variables based on at least said observations;changing the set of values of control variables using a stepwise adjustment of the control variables and a break criterion based on residue values of the state variables;performing a classification of at least one entity of the network in a state according to the set of control variables.2. The method of claim 1 , further comprising identifying at least one control variable to change based on at least said observations.3. The method of claim 1 , wherein identifying at least one target entity where to change the values of control variables based on at least said observations comprises:using the hydraulic model to calculate predicted values of a set of state variables comprising at least a water velocity and pressure at the nodes, said predicted values being associated to second time references;computing residue values of the subset of the state variables as a difference between predicted values and observations at the second time references;performing a statistical analysis of residue values at an entity of ...

PREDICTION ON TOP-DOWN SCENES BASED ON ACTION DATA

Techniques for determining predictions on a top-down representation of an environment based on vehicle action(s) are discussed herein. Sensors of a first vehicle (such as an autonomous vehicle) can capture sensor data of an environment, which may include object(s) separate from the first vehicle (e.g., a vehicle or a pedestrian). A multi-channel image representing a top-down view of the object(s) and the environment can be generated based on the sensor data, map data, and/or action data. Environmental data (object extents, velocities, lane positions, crosswalks, etc.) can be encoded in the image. Action data can represent a target lane, trajectory, etc. of the first vehicle. Multiple images can be generated representing the environment over time and input into a prediction system configured to output prediction probabilities associated with possible locations of the object(s) in the future, which may be based on the actions of the autonomous vehicle. 1. A system comprising:one or more processors; and receiving sensor data of an environment captured by a sensor of an autonomous vehicle;', 'receiving action data associated with a candidate action for the autonomous vehicle to perform in the environment, wherein the candidate action comprises one or more of a stay-in-lane action, a turn action, or a lane change action, and wherein the action data is indicative of the candidate action;', 'generating, based at least in part on the sensor data and the action data, a multi-channel image representing a top-down view of the environment, the multi-channel image representing a bounding box associated with a vehicle in the environment proximate the autonomous vehicle, one or more of kinematic information or semantic information associated with the vehicle, and the candidate action associated with the autonomous vehicle;', 'inputting the multi-channel image into a machine learned model trained to generate a heat map comprising a prediction probability of a possible location ...

Artificial intelligence device for controlling external device

An artificial intelligence device for controlling an external device includes a display unit, and a processor configured to acquire a distance between the artificial intelligence device and a first external device, determine whether the acquired distance is less than a reference distance, display a first operation menu item for controlling the first external device on the display unit when the acquired distance is less than the reference distance, acquire situation information when the acquired distance is equal to or greater than the reference distance, determine a second external device as an object to be controlled based on the acquired situation information, and display a second operation menu item for controlling the determined second external device on the display unit.

Machine learning of electrical system behavior, and related systems, apparatuses, and methods

The present disclosure is directed to machine learning of electrical power system behavior, and related systems, apparatuses, and methods. A controller of an electrical power system includes a data storage device configured to store model data indicating a model load power consumed by loads of the electrical power system. The controller also includes a processor configured to determine current data including current load power consumed by the loads, modify the model data by aggregating the model data with the current data, and determine a set of control values for a set of control variables to effectuate a change to operation of the electrical power system based, at least in part, on the model data.

MOTION SUPPORT SYSTEM, ACTION SUPPORT METHOD, PROGRAM, LEARNING APPARATUS, TRAINED MODEL, AND LEARNING METHOD

A walking training apparatus is a motion support system that includes a walking assistance apparatus as an assistance apparatus, a selected assistance level setting unit, a load data acquisition unit, an angle sensor as a displacement sensor, and an overall control unit as a control unit. The assistance apparatus assists a motion of a joint performed by a user. The assistance level setting unit sets an assistance level that is a level of a force exerted by the assistance apparatus. The load data acquisition unit acquires load data related to a load of the assistance apparatus. The displacement sensor detects a displacement of the joint. The control unit determines a recommended assistance level, which is an assistance level to be recommended, based on the assistance level, the load data, and an output of the displacement sensor, and outputs information about the determined recommended assistance level. 1. A motion support system comprising:an assistance apparatus configured to assist a motion of a joint performed by a user;a selected assistance level setting unit configured to set a selected assistance level, the selected assistance level being an assistance level to be exerted by the assistance apparatus;a load data acquisition unit configured to acquire load data regarding a load of the assistance apparatus;a displacement sensor configured to detect a displacement of the joint; anda control unit configured to determine, based on the selected assistance level, the load data, and an output of the displacement sensor, a recommended assistance level that is the assistance level to be recommended, and to output information about the determined recommended assistance level.2. The motion support system according to claim 1 , further comprising:a storage unit configured to store statistical data about a motion of the joint performed in the past, the statistical data being generated by collecting the assistance level, the load data, and the output of the displacement ...

OUTPUT DEVICE, CONTROL DEVICE, AND EVALUATION FUNCTION VALUE OUTPUT METHOD

An output device with which an operator can understand a progress state of machine learning from evaluation function values is provided. The output device includes: an information acquisition unit that acquires a plurality of evaluation function values which use servo data or are calculated using the servo data from a machine learning device that performs machine learning with respect to a servo control device that controls a servo motor that drives a shaft of a machine tool, a robot, or an industrial machine; and an output unit that outputs the plurality of acquired evaluation function values. The output unit may include a display unit that displays the plurality of evaluation function values on a display screen. 1. An output device comprising: an information acquisition unit that acquires a plurality of evaluation function values which use servo data or are calculated using the servo data from a machine learning device that performs machine learning with respect to a servo control device that controls a servo motor that drives a shaft of a machine tool , a robot , or an industrial machine; andan output unit that outputs the plurality of acquired evaluation function values.2. The output device according to claim 1 , whereinan the output unit includes a display unit that displays the plurality of evaluation function values on a display screen.3. The output device according to claim 2 , further comprising:a drawing plotting unit that creates a drawing indicating change over time in the plurality of evaluation function values during machine learning, wherein the output unit displays the created drawing on the display screen.4. The output device according to claims 1 , whereinan the output unit outputs a smallest value of the plurality of evaluation function values.5. The output device according to claim 1 , whereinan the output unit outputs a smallest value of all the evaluation function values acquired from the start of machine learning.6. The output device according ...

MANAGING CONSUMER ENERGY DEMAND

A computer-implemented method, according to one embodiment, includes: receiving an energy consumption profile which spans multiple intervals in a period of time, and predicting a net energy demand of a consumer system over the period of time. Moreover, a first multiple is determined which, when applied to the received energy consumption profile, produces an updated energy consumption profile which corresponds to an amount of energy that is capable of satisfying the predicted net energy demand of the consumer system. A greatest amount of underprediction is estimated. A greatest amount of overprediction is also estimated. Furthermore, an initial state of an energy storage device electrically coupled to the consumer system is computed according to the updated energy consumption profile. The initial state of the energy storage device is also based on a second multiple applied to each of the greatest amount of underprediction, and the greatest amount of overprediction. 1. A computer-implemented method , comprising:receiving an energy consumption profile which spans multiple intervals in a period of time;predicting a net energy demand of a consumer system over the period of time;determining a first multiple which, when applied to the received energy consumption profile, produces an updated energy consumption profile which corresponds to an amount of energy that is capable of satisfying the predicted net energy demand of the consumer system;estimating a greatest amount of underprediction by which the predicted net energy demand of the consumer system underpredicts an actual net energy demand of the consumer system over the period of time;estimating a greatest amount of overprediction by which the predicted net energy demand of the consumer system overpredicts the actual net energy demand of the consumer system over the period of time; andcomputing an initial state of an energy storage device electrically coupled to the consumer system which is able to satisfy the actual ...

ROLLING PROCESS LEARNING CONTROL DEVICE

An instantaneous value of a learning coefficient is calculated based on a gap between a result value and a result recalculation value, and an update value of the learning coefficient is calculated from the instantaneous value. The calculated update value is recorded in a cell corresponding to present rolling conditions. At the time of setup calculation, the predetermined number of neighboring cells having small spatial distances from a target cell corresponding to next rolling conditions in a space having rolling conditions as coordinate axes are selected from cells in which respective evaluation results of recency, saturation, and stability of the learning coefficient satisfy criteria. An estimation value of the learning coefficient in the target cell is then calculated by polynomial interpolation using representative values of the learning coefficients in the selected neighboring cells. The most recent update value of the learning coefficient in the target cell is then corrected with the estimation value, and the corrected value is decided as a use value of the learning coefficient in the next rolling conditions. 1. A rolling process learning control device that has a database including a plurality of cells that divide rolling conditions , and manages using the database a learning coefficient of a model expression used for setup calculation of a rolling process , the rolling process learning control device comprising:a processor to execute a program; and an instantaneous value calculation recording unit that calculates an instantaneous value of the learning coefficient based on a gap between a result value measured in the rolling process and a result recalculation value calculated using the model expression, and records the instantaneous value in a cell corresponding to present rolling conditions together with a learning time;', 'an update value calculation recording unit that calculates an update value of the learning coefficient based on the instantaneous value ...

COMPUTING DEVICE, MACHINE LEARNING METHOD, AND STORAGE MEDIUM

A computing device performs computation for controlling operations of a mobile manipulator configured to hold a plurality of target objects with a manipulator and move the target objects to predetermined positions. The computing device includes a storage and a calculator. The storage stores a trained machine learning model trained by inputting a plurality of training data sets, which are combinations of state variables and pieces of determination data associated with the state variables. The training data sets are acquired in advance. The calculator outputs a movement-target object to be moved to a predetermined position at current time by inputting the state variable to the trained machine learning model read from the storage. The state variable contains relative positions of the target objects to a specific portion of the mobile manipulator. The determination data associated with the state variable represents the movement-target object. 1. A computing device configured to perform computation for controlling operations of a mobile manipulator configured to hold a plurality of target objects with a manipulator and move the target objects to predetermined positions , the computing device comprising:a storage configured to store a trained machine learning model trained by inputting a plurality of training data sets, which are combinations of state variables and pieces of determination data associated with the state variables, the training data sets being acquired in advance; anda calculator configured to output a movement-target object to be moved to a predetermined position at current time by inputting a state variable to the trained machine learning model read from the storage, whereinthe state variable contains relative positions of the target objects to a specific portion of the mobile manipulator, andthe determination data associated with the state variable represents the movement-target object.2. The computing device according to claim 1 , wherein the state ...

ONLINE LEARNING AND VEHICLE CONTROL METHOD BASED ON REINFORCEMENT LEARNING WITHOUT ACTIVE EXPLORATION

A computer-implemented method of adaptively controlling an autonomous operation of a vehicle is provided. The method includes steps of (a) in a critic network in a computing system configured to autonomously control the vehicle, determining, using samples of passively collected data and a state cost, an estimated average cost, and an approximated cost-to-go function that produces a minimum value for a cost-to-go of the vehicle when applied by an actor network; and (b) in an actor network in the computing system and operatively coupled to the critic network, determining a control input to apply to the vehicle that produces the minimum value for the cost-to-go, wherein the actor network is configured to determine the control input by estimating a noise level using the average cost, a cost-to-go determined from the approximated cost-to-go function, a control dynamics for a current state of the vehicle, and the passively collected data. 1. A computer-implemented method of adaptively controlling an autonomous operation of a vehicle , the method comprising:a) in a critic network in a computing system configured to autonomously control the vehicle, determining, using samples of passively collected data and a state cost, an estimated average cost, and an approximated cost-to-go function that produces a minimum value for a cost-to-go of the vehicle when applied by an actor network; andb) in an actor network in the computing system and operatively coupled to the critic network, determining a control input to apply to the vehicle which produces the minimum value for the cost-to-go,wherein the actor network is configured to determine the control input by estimating a noise level using the estimated average cost, an estimated cost-to-go determined from the approximated cost-to-go function, a control dynamics for a current state of the vehicle, and the samples of passively collected data.4. The method of further comprising the step of updating parameters of the critic network ...

DRIVE ASSIST DEVICE

In a drive assist system, a map data acquiring section acquires at least one of a driver's operation ability and a load of a vehicle. An adjustment section determines an assist control amount as a control parameter of drive assist for the vehicle so that a degree of the driver's operation is increased according to reduction of the driver's operation ability or increasing of the load of the vehicle. An assist control amount calculation section transmits the assist control amount to a steering motor and a notification section so as to execute the drive assist for the vehicle. 1. A drive assist device which executes a drive assist of an own vehicle , comprising a computer system including a central processing unit , the computer system being configured to provide:an ability acquiring section which acquires at least one of a driver's operation ability of the own vehicle, and an operating load of the own vehicle;a control amount determination section which determines an assist control amount as a control parameter of the drive assist of the own vehicle so that a degree of the driver's operation for the own vehicle is increased according to reduction of the degree of the driver's operation ability, and increasing of the operating load of the own vehicle; andan assist execution section which transmits the assist control amount to the assist section in order to execute drive assist for the own vehicle.2. The drive assist device according to claim 1 , wherein the control amount determination section determines a steering control amount as the assist control amount claim 1 , andthe assist execution section transmits the assist control amount determined by the control amount determination section to the assist section which executes the drive assist for the own vehicle.3. The drive assist device according to claim 1 , wherein the control amount determination section determines the assist control amount so that an assist start timing claim 1 , at which the drive assist is ...

DETERMINATION OF TASK AUTOMATION USING AN ARTIFICIAL INTELLIGENCE MODEL

A device may process, using a first model and based on an entity-specific task description that is included in entity role data and that is associated with a role, the entity role data to identify a task associated with the role. The device may determine, using a second model and based on the entity-specific task description and standardized descriptions of automation-capable tasks, a task automation score associated with the task. The device may determine, using a third model and based on a characteristic of the task and mappings of standardized characteristics to a plurality of automation categories, a set of automation category scores for the task. The device may classify, based on the set of automation category scores, the task as being associated with a particular automation category, and may perform an action associated with the task automation score and the particular automation category. 1. A method , comprising:receiving, by a device, entity role data that is associated with a role of an entity; 'wherein the first model is configured to identify the task based on an entity-specific task description that is included in the entity role data and that is associated with the role;', 'processing, by the device and using a first model, the entity role data to identify a task associated with the role,'} 'wherein the second model is configured to determine the task automation score based on the entity-specific task description and standardized task descriptions of automation-capable tasks;', 'determining, by the device and using a second model, a task automation score associated with the task,'} 'wherein the third model is configured to determine the set of automation category scores based on a characteristic of the task and standardized characteristics that are mapped to a plurality of automation categories;', 'determining, by the device and using a third model, a set of automation category scores for the task,'}classifying, by the device and based on the set of ...

Building control system using reinforcement learning

A method of operating a building management system is disclosed. The method includes determining, by a processing circuit, policy rankings for a plurality of control policies based on building operation data of a first previous time period, selecting, by the processing circuit, a set of control policies from among the plurality of control policies based on the policy rankings of the set of control policies satisfying a ranking threshold, generating, by the processing circuit, a plurality of prediction models for the set of control policies, selecting, by the processing circuit, a first prediction model of the plurality of prediction models based on building operation data of a second previous time period, and responsive to selecting the first prediction model, operating, by the processing circuit, the building management system using the first prediction model.

METHOD AND DEVICE FOR PRODUCING A PRODUCT AND COMPUTER PROGRAM PRODUCT

The disclosure relates to a method and a device for producing a product and to a computer program product. The product is produced in at least one production step. A quality control check is optionally carried out after at least one of the production steps to determine a quality index of the product in question. To save on the quality control check, a quality indicator of the product in question is determined using production data. The production data are advantageously provided by sensors. The quality indicator of the product in question may be calculated using an adaptive algorithm. The adaptive algorithm may be taught and/or improved using quality indices of a quality control unit and the corresponding production data. The adaptive algorithm may be taught with the aid of a further computing unit, in particular in a cloud. 1. A method comprising:producing a circuit board in at least one production step;providing production data during each production step of the at least one production step, wherein the production data is a position of an applied solder paste on the circuit board, a deviation of the applied solder paste in relation to a target position or a target pattern, a thickness of a layer of the applied solder paste, a temperature or an air humidity of an environment of the circuit board, or a combination thereof;calculating a quality indicator based on the respective production data; andassociating the quality indicator with the circuit board,2. The method of claim 1 , wherein the respective quality indicator is associated with the circuit board with aid of a database or a marking on the circuit board claim 1 ,3. The method of claim 1 , wherein claim 1 , after the at least one production step claim 1 , a quality control check takes place claim 1 , andwherein, during the quality control check, in each case a quality index is associated with the circuit board.4. The method of claim 3 , wherein the quality indicator is determined with aid of a learning- ...

ELEVATOR HEALTH MONITORING SYSTEM

An elevator system includes a component adapted to perform a function, a sensor, and a control configuration. The sensor is configured to detect an operating parameter associated with the function. The control configuration is configured to receive a parameter signal from the sensor, and extract a predesignated feature from data associated with the parameter signal. The predesignated feature is then aggregated by the control configuration and machine learning is applied to determine a degradation level of the function associated with the predesignated feature. 1. An elevator system comprising:a component adapted to perform a function;a sensor configured to detect an operating parameter associated with the function; anda control configuration configured to receive a parameter signal from the sensor; extract a predesignated feature from data associated with the parameter signal, aggregate the predesignated feature, and apply machine learning to determine a degradation level of the function associated with the predesignated feature.2. The elevator system set forth in claim 1 , further comprising:a car adapted to travel in a hoistway, wherein the component includes a door assembly adapted to open and close for user access into and out of the car from and to a plurality of landings.3. The elevator system set forth in claim 2 , wherein the door assembly includes a plurality of landing doors and the function is opening and closing of the plurality of landing doors claim 2 , wherein the sensor is one of a plurality of sensors with each sensor located at a respective landing door of the plurality of landing doors.4. The elevator system set forth in claim 3 , wherein the feature includes vibration.5. The elevator system set forth in claim 2 , wherein the door assembly includes a car door supported by the car and the function is opening and closing the car door.6. The elevator system set forth in claim 5 , wherein the feature includes vibration.7. The elevator system set forth ...

RIDER RECOGNITION DEVICE FOR HUMAN-POWERED VEHICLE AND CONTROL SYSTEM OF HUMAN-POWERED VEHICLE

To provide a rider recognition device for a human-powered vehicle and a control system of a human-powered vehicle that improve the usability, a rider recognition device for a human-powered vehicle includes a detector and an artificial intelligence processing unit. The detector detects state information while the human-powered vehicle is traveling. The state information is related to at least one of a state of the human-powered vehicle and a state of a rider of the human-powered vehicle. The artificial intelligence processing unit recognizes the rider corresponding to the state information detected by the detector. 1. A rider recognition device for a human-powered vehicle , the rider recognition device comprising:a detector configured to detect state information while the human-powered vehicle is traveling, wherein the state information is related to at least one of a state of the human-powered vehicle and a state of a rider of the human-powered vehicle; andan artificial intelligence processing unit including an arithmetic processing device configured to recognize the rider corresponding to the state information detected by the detector.2. The rider recognition device according to claim 1 , further comprising an input device configured to input personal information related to the rider claim 1 , wherein the artificial intelligence processing unit configured to build a process for recognizing the rider in accordance with the personal information input from the input device and the state information detected by the detector.3. The rider recognition device according to claim 1 , wherein the artificial intelligence processing unit is configured to learn characteristics of changes in the state information detected by the detector.4. The rider recognition device according to claim 3 , wherein the artificial intelligence processing unit further includes first storage configured to store learned information.5. The rider recognition device according to claim 2 , wherein the ...

CREATION DEVICE, COMPONENT CONTROL DEVICE, CREATION METHOD, COMPONENT CONTROL METHOD, COMPUTER PROGRAM AND LEARNING MODEL

A creation device is provided that has at least one processor operatively coupled to non-transitory computer readable storage to execute operations that includes an acquisition part and a creation part. The acquisition part acquires input information concerning traveling of a human-powered vehicle. The creation part uses a learning algorithm to create a learning model that outputs output information concerning control of the components of the human-powered vehicle based on the input information. 1. A creation device comprising:a non-transitory computer readable storage having a learning algorithm stored in the non-transitory computer readable storage; andat least one processor operatively coupled to the non-transitory computer readable storage to execute operations including:an acquisition part configured to acquire input information concerning traveling of a human-powered vehicle; anda creation part configured to use the learning algorithm to create a learning model that outputs output information concerning control of a component of the human-powered vehicle based on the input information.2. The creation device according to claim 1 , whereinthe output information is at least one of a gear stage and a gear ratio for a transmission.3. The creation device according to claim 1 , whereinthe input information includes at least one of a traveling speed of the human-powered vehicle and a cadence of a crank of a driving mechanism.4. The creation device according to claim 1 , whereinthe input information includes detection data of an attitude of the human-powered vehicle.5. The creation device according to claim 1 , whereinthe input information includes detection data of a posture of a user riding on the human-powered vehicle.6. The creation device according to claim 1 , whereinthe input information includes detection data of a traveling environment of the human-powered vehicle.7. The creation device according to claim 1 , whereinthe acquisition part is configured to ...

Energy management system, energy management method, and recording medium storing an energy management program

An energy management system includes a memory that stores electricity consumption amount of a target object separately for each one of a plurality of operational status of the target object, the electricity consumption amount being measured by an electricity measurement unit, and a processor that obtains information indicating the operational status of the target object for each day in the future from a calendar and predicts future electricity consumption amount for each day in the future, using the operational status of the target object for each day and the electricity consumption amount stored for each operational status.

Dynamic contingency avoidance and mitigation system

The disclosed subject matter provides systems and methods for allocating resources within an infrastructure, such as an electrical grid, in response to changes to inputs and output demands on the infrastructure, such as energy sources and sinks. A disclosed system includes one or more processors, each having respective communication interfaces to receive data from the infrastructure, the data comprising infrastructure network data, one or more software applications, operatively coupled to and at least partially controlling the one or more processors, to process and characterize the infrastructure network data; and a display, coupled to said one or more processors, for visually presenting a depiction of at least a portion of the infrastructure including any changes in condition thereof, and one or more controllers in communication with the one or more processors, to manage processing of the resource, wherein the resource is obtained and/or distributed based on the characterization of said real time infrastructure data.

Central plant control system with computation reduction based on graph theory

Systems and methods for predicting a plurality of thermodynamic states of a plurality of heat, ventilation, and air conditioning (HVAC) devices of an energy plant are disclosed. The system includes a processor and a non-transitory computer readable medium storing instructions when executed causing the processor to: obtain plant netlist data describing the plurality of HVAC devices of the energy plant and connections of the plurality of HVAC devices to corresponding nodes; identify, from the plurality of thermodynamic states of the energy plant at a plurality of nodes, a reduced subset of the plurality of thermodynamic states to be predicted based on the connections of the plurality of HVAC devices; predict the reduced subset of the plurality of thermodynamic states using a non-linear solver; and determine the plurality of thermodynamic states of the energy plant based on the reduced subset of the predicted thermodynamic states.

MODULAR CONTROL SYSTEM

Embodiments are directed towards automatically identifying, configuring, monitoring, controlling, managing, and maintaining a machine, via collection computers in communication with the machine components. The components include ID Tags that store identification data, such as a component type and a unique identifier. Interrogation of the ID Tags enables the automatic identification and configuration of the machine. Data provided by the sensors, during usage of the machine, enables the remote monitoring and managing of the usage, as well as maintaining of the machine. Machine maintenance includes automatically predicting and scheduling the replacement of various components. Embodiments provide suggestions for suppliers of replacement components, as well as suggestions for alternative components that may be better optimized for the configuration and usage of the machine. Heuristics and crowd-generated data, via machine user social networks, inform predictive analyses employed to automatically identify, configure, manage, operate, and maintain the machine. 1communicating, to a collection computer, component identification data separately stored in each of a plurality of component identification (ID) Tags that correspond to one or more components for the machine, wherein the component identification data includes a component type;determining a combination of the component types based on at least the component identification data;automatically determining a machine type for the machine based on a comparison of the combination of the component types and one or more previously provided combinations of component types that correspond to a previously determined machine type;automatically determining a machine configuration for the machine based on one or more of the machine type and the combination of component types, wherein the machine configuration includes one or more component configurations for each component that corresponds to one or more of the plurality of ...

Systems and methods for automated wetstock management

An automated wetstock management system can include a plurality of sensors disposed in a fuel storage facility, the plurality of sensors configured to sense fuel data characterizing one or more aspects of the fuel storage facility, and a wetstock management server communicatively coupled to the plurality of sensors. The wetstock management server can process the fuel data to detect whether the fuel data satisfies an exception indicative of an operational issue of the fuel storage facility based on one or more predefined rules or models stored in the wetstock management server. In some embodiments, the wetstock management server can generate a workflow for assisting a user of the fuel storage facility to resolve the operational issue. In some embodiments, the wetstock management server can assign a risk category to the exception and electronically transmit an alert characterizing the operational issue to the user.

Vehicle occupant data collection and processing with artificial intelligence

A server includes an interface, programmed to receive, from a vehicle, vehicle data indicative of vehicle status and user data indicative of usage of vehicle features by a user; and a processor, programmed to analyze the vehicle data and the user data using artificial intelligence (AI) logic to generate a comfort prediction for the user; and configure a comfort device associated with the user, external to the vehicle, using the comfort prediction.

AUTOMATION SYSTEM AND WEAR DETECTION CONTROLLER

A machine or autonomous system includes a diagnostic controller and is configured to perform a method for monitoring health of a machine. The method includes monitoring a set of first electrical signals indicative of control of a motor of the machine while the machine is operated in a first autonomous mode, determining that an abnormal operating condition has occurred in response to the set of first electrical signals meeting a first criteria, having the machine operate in a test mode in response to the determination that the abnormal operating condition has occurred, monitoring a set of second electrical signals indicative of control of the motor during the test mode, and determining a fault condition in response to the set of second electrical signals meeting a second criteria. 1. A method for monitoring health of a machine , the method comprising:monitoring a set of first electrical signals indicative of control of a motor of the machine while the machine is operated in a first autonomous mode;determining that an abnormal operating condition has occurred in response to the set of first electrical signals meeting a first criteria;having the machine operate in a test mode in response to the determination that the abnormal operating condition has occurred;monitoring a set of second electrical signals indicative of control of the motor during the test mode; anddetermining a fault condition in response to the set of second electrical signals meeting a second criteria.2. The method according to claim 1 , wherein the set of first electrical signals is indicative of numerical control of the motor or is indicative of a mechanical response of a subsystem.3. The method according to claim 2 , wherein the set of first electrical signals includes at least one of encoder position and following error.4. The method according to claim 1 , wherein the set of first electrical signals includes drive current of the motor.5. The method according to further comprising one of the ...

Approximate value iteration with complex returns by bounding

A control system and method for controlling a system, which employs a data set representing a plurality of states and associated trajectories of an environment of the system; and which iteratively determines an estimate of an optimal control policy for the system. The iterative process performs the substeps, until convergence, of estimating a long term value for operation at a respective state of the environment over a series of predicted future environmental states; using a complex return of the data set to determine a bound to improve the estimated long term value; and producing an updated estimate of an optimal control policy dependent on the improved estimate of the long term value. The control system may produce an output signal to control the system directly, or output the optimized control policy. The system preferably is a reinforcement learning system which continually improves.

INFORMATION PROCESSING APPARATUS, METHOD, AND PROGRAM

The present disclosure relates to an information processing apparatus, a method, and a program capable of causing a system to efficiently learn a method of controlling a person. A control learning system calculates a reward based on an input objective state of a control target and a state of the control target based on a sensing result of the control target. The control learning system performs reinforcement learning using the calculated reward and the state of the control target to select a better action for bringing the control target closer to the objective state. The control learning system executes the selected action for the control target. For example, the present disclosure can be applied to a control learning system including a terminal and a cloud system. 1. An information processing apparatus comprising:a reward calculating part configured to calculate a reward based on an input objective state of a control target and a state of the control target based on a sensing result of the control target;a reinforcement learning part configured to perform reinforcement learning using the reward calculated by the reward calculating part and the state of the control target to select a better action for bringing the control target closer to the objective state; andan action execution part configured to execute the action selected by the reinforcement learning part for the control target.2. The information processing apparatus according to claim 1 , further comprising:a cause-and-effect analyzing part configured to perform a cause-and-effect analysis on the action executed for the control target; andan action adding part configured to add, as a result of the cause-and-effect analysis performed by the cause-and-effect analyzing part, a better action for bringing the control target closer to the objective state.3. The information processing apparatus according to claim 2 , further comprising:a notifier configured to notify regarding the action added by the action adding ...

NUMERICAL CONTROL DEVICE

A numerical control device includes: a tool-side displacement measurement unit; a workpiece-side displacement measurement unit; a drive signal measurement unit; a relative displacement calculation unit between the tool and the workpiece; a relative displacement prediction unit calculating a relative displacement predicted value from the drive signal, from a prediction model representing a relationship between the drive signal and the relative displacement; a model parameter operation unit generating prediction model parameters constituting the prediction model, from the drive signal, the relative displacement, and the predicted value; and a command value correction unit outputting a post-correction position command obtained by correcting a position command to the drive unit using the prediction model parameters. The model parameter operation unit changes the prediction model parameters to reduce a difference between the relative displacement and the predicted value. 1. A numerical control device for controlling a relative displacement between a tool and a workpiece in a machine tool using a command to drive circuitry driving a motor , the numerical control device comprising:tool-side displacement measurement circuitry to measure a physical quantity related to a displacement of the tool;workpiece-side displacement measurement circuitry to measure a physical quantity related to a displacement of the workpiece;drive signal measurement circuitry to measure a drive signal outputted from the drive circuitry to the motor;relative displacement calculation circuitry to calculate a relative displacement between the tool and the workpiece from the physical quantity related to the displacement of the tool and the physical quantity related to the displacement of the workpiece;relative displacement prediction circuitry to calculate a relative displacement predicted value that is a predicted value of the relative displacement from the drive signal, based on a prediction model ...

Diagnostic Device and Method for Monitoring a Technical Plan

A diagnostic device for monitoring the operation of a technical plant with an automation system, wherein the diagnostic device includes a data memory in which at least one data set characterizing the operation of the plant with values of process variables can be stored, and an evaluation device, where the diagnostic device is characterized in that the evaluation device is configured to determine a diagnostic statement about the operation of the technical plant based on the data set and at least one self-organizing map and based on a program for controlling a sequence during the operation of the technical plant with repeatedly traversed step sequences via a Dynamic Time Warping method. 1. A diagnostic device for monitoring the operation of a technical plant with an automation system , the diagnostic device comprising:a data memory in which at least one data set characterizing the operation of the plant with values of process variables is storable; andan evaluation device;wherein the evaluation device is configured to determine a diagnostic statement about the operation of the plant based on the at least one data set, at least one self-organizing map and a program for controlling the sequence during the operation of the plant with repeatedly traversed step sequences via a Dynamic Time Warping method.2. A method for monitoring a technical plant , historical data of a process step having previously been repeatedly executed on the technical plant being retrievable and evaluatable , and the process step includes a plurality of temporal sub-steps , comprising:a) acquiring manipulated variables, measured values, decision variables and measurable disturbance variables which are tapable as historical data of the technical plant with a framework of completed passes of the process step;b) learning previously acquired data in at least one self-organizing map, nodes of the at least one self-organizing map representing individual temporal sub-steps during a pass of the process ...

MOBILE ROBOT, AND CONTROL METHOD OF MOBILE ROBOT

Provided is a control method of a mobile robot, the method including an experience information generating step of obtaining current state information through sensing during traveling, and, based on a result of controlling an action according to action information selected by inputting the current state information to a predetermined action control algorithm for docking, generating one experience information that comprises the state information and the action information. The control method may further include an experience information collecting step of storing a plurality of experience information by repeatedly performing the experience information generating step, and a learning step of learning the action control algorithm based on the plurality of experience information. 1. A mobile robot , comprising:a main body;a traveler configured to move the main body;a sensing unit configured to perform sensing during traveling to obtain current state information; anda controller configured to, based on a result of controlling an action according to action information selected by inputting the current state information to a predetermined action control algorithm for docking, generate one experience information including the state information and the action information, repeatedly perform the generating of the experience information to store a plurality of experience information, and learn the action control algorithm based on the plurality of experience information.2. A control method of a mobile robot , the method comprising:an experience information generating step of obtaining current state information through sensing during traveling, and, based on a result of controlling an action according to action information selected by inputting the current state information to a predetermined action control algorithm for docking, generating one experience information that comprises the state information and the action information;an experience information collecting step of ...

OFF ROAD ASSISTANCE

A method for off road driving, the method may include obtaining environment sensed information about an environment of a vehicle of a certain model, by one of more vehicle sensors of the vehicle and while driving over an off road path; detecting, by a machine learning process, an off road driving event; determining, by the machine learning process, a characteristic behavior of vehicles of the certain model when facing the off road driving event; and responding, at least in part by the machine learning process, to the occurrence of the off road driving event. 1. A method for off road driving , the method comprises:obtaining environment sensed information about an environment of a vehicle of a certain model, by one of more vehicle sensors of the vehicle and while driving over an off road path;detecting, by a machine learning process, an off road driving event;determining, by the machine learning process, a characteristic behavior of vehicles of the certain model when facing the off road driving event; andresponding, at least in part by the machine learning process, to the occurrence of the off road driving event.2. The method according to wherein the machine learning process was trained by a training process that comprises:obtaining off-road sensed information sensed by vehicles of the certain model; wherein the off-road sensed information comprises environment off-road sensed information and off-road telematic sensed information indicative of behaviors of vehicles of the certain model;clustering the off-road environment sensed information to provide first clusters; andgenerating second clusters, whereas different second clusters are associated with different characteristic behaviors of vehicles of the certain model when facing different off road driving events; wherein the generating of the second clusters comprises clustering the first clusters based on off-road telematic sensed information associated with the off-road environment sensed information of the first ...

AUTOMATED VALIDATION, ESTIMATION, AND EDITING CONFIGURATION SYSTEM

An apparatus for configuring validation, estimation, and editing (VEE) rules for performing VEE on interval-based energy consumption streams includes a data stores, a rules processor, and a process control element. The stores provides tagged data sets each associated with a corresponding one of the streams, each of the sets comprising groups of contiguous interval values tagged as having been validated. The rules processor reads the stores upon initiation of an event and, for the each of the sets, creates anomalies having different durations using only the groups of values, the groups of values corresponding to correct data, and generates estimates for the anomalies by employing estimation techniques for each of the durations and, for the each of the durations, selects a corresponding one of the techniques for subsequent employment when performing VEE of subsequent energy consumption data associated with the each of the durations for the corresponding one of the streams. The control element executes functions on the streams translated by the rules processor, and directs one or more system elements to change state. 1. An apparatus for configuring validation , estimation , and editing (VEE) rules for performing VEE on interval-based energy consumption streams , the apparatus comprising:a post VEE readings data stores, configured to provide tagged energy consumption data sets that are each associated with a corresponding one of the interval-based energy consumption streams, each of said tagged energy consumption data sets comprising groups of contiguous interval values tagged as having been validated;a rules processor, configured to read said post VEE readings data stores upon initiation of an event and, for said each of said tagged energy consumption data sets, configured to create anomalies having different durations using only said groups of contiguous interval values, said groups of contiguous interval values corresponding to correct data, and configured to ...

AUTOMATED DETECTION AND CORRECTION OF VALUES IN ENERGY CONSUMPTION STREAMS

An apparatus for configuring validation, estimation, and editing (VEE) rules for performing VEE on interval-based energy consumption streams includes a data stores, a rules processor, and a process control element. The stores provides tagged data sets each associated with a corresponding one of the streams, each of the sets comprising groups of contiguous interval values tagged as having been validated. The rules processor reads the stores upon initiation of an event and, for the each of the sets, creates anomalies having different durations using only the groups of values, the groups of values corresponding to correct data, and generates estimates for the anomalies by employing estimation techniques for each of the durations and, for the each of the durations, selects a corresponding one of the techniques for subsequent employment when performing VEE of subsequent energy consumption data associated with the each of the durations for the corresponding one of the streams. The control element executes functions on the streams translated by the rules processor, and directs one or more system elements to change state. 1. An apparatus for configuring validation , estimation , and editing (VEE) rules for performing VEE on interval-based energy consumption streams , the apparatus comprising:a VEE processor, configured to detect and correct one or more adjacent points in the interval-based energy consumption streams that appear to be erroneous;a post VEE readings data stores, configured to provide tagged energy consumption data sets that are each associated with a corresponding one of the interval-based energy consumption streams, each of said tagged energy consumption data sets comprising groups of contiguous interval values tagged as having been validated;a rules processor, configured to read said post VEE readings data stores upon initiation of an event and, for said each of said tagged energy consumption data sets, configured to create anomalies having different ...

Providing domain models for industrial systems

Hidden Features are locally extracted from Industrial Data of the industrial system by a Local Application executed on a local computer of a customer. The Hidden Features are uploaded to an external computer of a service provider. A Domain Model for the industrial system is externally determined from an Industrial Model Library (IML) on the external computer based on the uploaded Hidden Features by an External Algorithm including at least one Machine Learning Model (MLM) executed on the external computer. The determined Domain Model for the industrial system is provided to the customer. The at least one MLM has been trained on ranking most appropriate Domain Models for industrial systems based on Hidden Features of the respective industrial systems. The most appropriate Domain Models represent all relevant technical aspects of the respective industrial systems.

INTELLIGENT OPERATION CONTROL APPARATUS AND SYSTEM

The present disclosure provides an intelligent operation control apparatus and system. The apparatus includes: a plurality of intelligent operation control systems; the intelligent operation control system is configured to include edge intelligent operation control systems, second-level intelligent operation control systems and nth-level intelligent operation control systems, wherein n is an integer greater than or equal to 2; each intelligent operation control system includes an operation hub and at least one intelligent operation control terminal; the operation hub is at least one server; the IoT of the industrial Internet can be quickly built, thereby enabling digital upgrade of the industry. 1. An intelligent operation control apparatus , comprising a plurality of intelligent operation control systems; wherein the intelligent operation control system is configured to comprise edge intelligent operation control systems , second-level intelligent operation control systems and nth-level intelligent operation control systems; wherein n is an integer greater than or equal to 2;a plurality of the edge intelligent operation control systems are connected to one of the second-level intelligent operation control systems;a plurality of the second-level intelligent operation control systems are connected to one of the third-level intelligent operation control systems; the rest of intelligent operation control systems are connected in this manner;each of the intelligent operation control systems comprises an operation hub and at least one intelligent operation control terminal;the operation hub is connected to all the intelligent operation control terminals; and the operation hub is at least one server.2. The intelligent operation control apparatus according to claim 1 , wherein the intelligent operation control terminal comprises: a processor claim 1 , a northbound communication module claim 1 , a southbound communication module and a human-computer interaction interface; ...

CONTROL TOWER AND ENTERPRISE MANAGEMENT PLATFORM WITH ROBOTIC PROCESS AUTOMATION SYSTEMS

A value chain system that provides recommendations for designing a logistics system generally includes a machine learning system that trains machine-learned models that output logistics design recommendations based on training data sets that each respectively defines one or more features of a respective logistic system and an outcome relating to the respective logistics system; an artificial intelligence system that receives a request for a logistics system design recommendation and determines the logistics system design recommendation based on one or more of the machine-learned models and the request; and a digital twin system that generates an environment digital twin of a logistics environment that incorporates the logistics system design recommendation, and one or more physical asset digital twins of physical assets. The digital twin system executes a simulation based on the logistics environment digital twin, the one or more physical asset digital twins. 1. An information technology system , comprising:a cloud-based management platform with a micro-services architecture, the platform having a set of interfaces that are configured to access and configure features of the platform, a set of network connectivity facilities that are configured to direct a set of value chain network entities to connect to the features of the platform, a set of adaptive intelligence facilities that are configured to automate a set of capabilities of the platform related to at least one of the value chain network entities and the features of the platform, a set of data storage facilities that are configured to store data collected and handled by the platform, or a set of monitoring facilities that are configured to monitor the value chain network entities, wherein the interfaces, the network connectivity facilities, the adaptive intelligence facilities, the data storage facilities, and the monitoring facilities are coordinated for monitoring and management of the value chain network ...

CONTROL TOWER AND ENTERPRISE MANAGEMENT PLATFORM WITH ROBOTIC PROCESS AUTOMATION SYSTEMS MANAGING PRODUCT OUTCOMES AND ACTIVITIES

A value chain system that provides recommendations for designing a logistics system generally includes a machine learning system that trains machine-learned models that output logistics design recommendations based on training data sets that each respectively defines one or more features of a respective logistic system and an outcome relating to the respective logistics system; an artificial intelligence system that receives a request for a logistics system design recommendation and determines the logistics system design recommendation based on one or more of the machine-learned models and the request; and a digital twin system that generates an environment digital twin of a logistics environment that incorporates the logistics system design recommendation, and one or more physical asset digital twins of physical assets. The digital twin system executes a simulation based on the logistics environment digital twin, the one or more physical asset digital twins. 1. An information technology system , comprising:a cloud-based management platform with a micro-services architecture, the platform having a set of interfaces that are configured to access and configure features of the platform, a set of network connectivity facilities that are configured to direct a set of value chain network entities to connect to the features of the platform, a set of adaptive intelligence facilities that are configured to automate a set of capabilities of the platform related to at least one of the value chain network entities and the features of the platform, or a set of monitoring facilities that are configured to monitor the value chain network entities, wherein the interfaces, the network connectivity facilities, the adaptive intelligence facilities, and the monitoring facilities are coordinated for monitoring and management of the value chain network entities;a set of applications that are configured to direct an enterprise to manage the value chain network entities of the platform ...

AIR-CONDITIONING CONTROL SYSTEM AND AIR-CONDITIONING CONTROL METHOD

A heat load predictor predicts a change over time of a heat amount to be processed by air-conditioning equipment, an operation plan creator previously creates an operation plan of the air-conditioning equipment to reduce an evaluation index under a first restrictive condition that a total process heat load be maintained at a same level or within a range of a predetermined amount of difference and a room temperature be maintained within a predetermined comfortable temperature range, and an operation plan corrector corrects the operation plan during controlling the air-conditioning equipment based on the operation plan. If an actually measured temperature differs from a predicted temperature predicted by the operation plan creator at the time of creating the operation plan, the operation plan creator predicts a change over time of the temperature in the room, and corrects the operation plan to minimize the evaluation index under the first restrictive condition. 1. An air-conditioning control system configured to control air-conditioning equipment installed in a building , the air-conditioning control system comprising:a heat load prediction unit configured to predict a change over time of a heat amount to be processed by the air-conditioning equipment based on provided heat load prediction data;an operation plan creation unit configured to previously create an operation plan of the air-conditioning equipment in an air-conditioning operation plan application period to reduce one of a power consumption amount and a running cost of the air-conditioning equipment serving as an evaluation index under a first restrictive condition that a total process heat load be maintained at one of a same level and within a range of a predetermined amount of difference and that a temperature in a room be maintained within a predetermined comfortable temperature range;an operation plan correction unit configured to correct the operation plan in a predetermined cycle during execution of ...

Plasma Propulsion System Feedback Control

Systems and methods can support a plasma propulsion system. The system may include a thrust head comprising a plasma generator and a thrust generator. A propellant handling assembly may be directly coupled to the thrust head. The propellant handling assembly may comprise a manifold and a plurality of valves. A propellant storage vessel may be directly coupled to the propellant handling assembly. A propulsion control module may be operable to receive inputs associated with the plasma propulsion system, generate control outputs associated with the plasma propulsion system, establish and train models relating the inputs and the control outputs, apply the inputs to the models to update the output parameters, and apply the output parameters to control the plasma propulsion system. 1. A plasma propulsion system , comprising:a thrust head comprising a plasma generator and a thrust generator;a propellant handling assembly directly coupled to the thrust head, wherein the propellant handling assembly comprises a manifold and a plurality of valves;a propellant storage vessel directly coupled to the propellant handling assembly; anda propulsion control module operable to:receive inputs associated with the plasma propulsion system,generate control outputs associated with the plasma propulsion system,establish and train one or more models relating the inputs and the control outputs,apply received inputs to the one or more models to update the generated output parameters, andapply the generated output parameters to control the plasma propulsion system.2. The plasma propulsion system of claim 1 , wherein the one or more models seek to regulate performance metrics associated with the plasma propulsion system.3. The plasma propulsion system of claim 1 , wherein the plurality of valves comprise piezo micro-valves.4. The plasma propulsion system of claim 1 , wherein the manifold comprises a test port to access to a flow path between the plurality of valves.5. The plasma propulsion ...

AUTOMATION OF A PROGRAMMABLE DEVICE

A method and apparatus for a computer-implemented adaptive automation module comprising an event recorder to store one or more events for a predetermined period, and a timeline pattern generator logic to create a timeline for the predetermined period. The module further comprising marker creator logic to generate a marker to abstract the timeline data from the event data for controlling a device. 1. A method for automation of a controller comprising:receiving an event from a sensor, the event indicating a presence or absence of a person;recording a timeline pattern based on a record of events;establishing a marker on the timeline pattern based on the record of events;adjusting the marker to approximate location consistency of the events in the timeline;computing a weight for the marker that reflects time consistency of the events; andtriggering output based on the marker.2. The method of claim 1 , wherein the creating the timeline pattern further comprises:archiving events into an event histogram; andcollapsing the event histogram to create the timeline pattern.3. The method of claim 1 , wherein the sensor indicates presence of a device associated with the person.4. The method of claim 3 , wherein the sensor provides data to the controller using a network.5. The method of claim 1 , further comprising:associating the events with external data comprising at least one of: time of day information, ambient light information, weather information, pricing information, and demand response data.6. The method of claim 1 , wherein the weight for the marker is computed based on a time range of the marker and a number of events within the time range of the marker.7. The method of claim 1 , wherein generating a marker comprises claim 1 , for each slot in a timeline pattern:determining whether an activity value for a current slot in the timeline pattern matches an activity value for an subsequent slot in the timeline pattern; andadding a marker to a list of markers if the activity ...

Apparatus and Method for the Production of Solid Dosage Forms

An apparatus for the production of solid dosage forms is presented, wherein the apparatus comprises a material processing chamber which is operable for manufacturing a product according to a pre-set product formation process path. The apparatus has at least one sensor for continuously monitoring formation of the product in the material processing chamber during the product formation process non-invasively in real time by sensing at least one product functional attribute value and a means for comparing each sensed product functional attribute value with a desirable product functional attribute value for that point on the product formation process path. A controller controls operation of the material processing chamber in response to the sensed product functional attribute value for maintaining the product on the product formation process path. 1. Apparatus for the production of solid dosage forms , comprising:a material processing chamber which is operable for manufacturing a product according to a pre-set product formation process path;at least one sensor for continuously monitoring formation of the product in the material processing chamber during the product formation process non-invasively in real time by sensing at least one product functional attribute value;means for comparing each sensed product functional attribute value with a desirable product functional attribute value for that point on the product formation process path; anda controller for controlling operation of the material processing chamber in response to the sensed product functional attribute value for maintaining the product on the product formation process path.2. Apparatus as claimed in where two on-line sensors are provided claim 1 , namely a first sensor and a second sensor claim 1 , wherein the first sensor senses a first desirable product functional attribute value and the second sensor senses a second desirable product functional attribute value claim 1 , the second desirable product ...

Data Processing Method for Care-Giving Robot and Apparatus

A data processing method for a care-giving robot and an apparatus comprises receiving data from a target object comprising a capability parameter of the target object, generating a growing model capability parameter matrix of the target object that includes the capability parameter, a capability parameter adjustment value, and a comprehensive capability parameter that is calculated based on the capability parameter; adjusting the capability parameter adjustment value in the growing model capability parameter matrix, to determine an adjusted capability parameter adjustment value; determining whether the adjusted capability parameter adjustment value exceeds a preset threshold; and sending the adjusted capability parameter adjustment value to a machine learning engine when the adjusted capability parameter adjustment value is within a range of the preset threshold. 1. A data processing method for a care-giving robot , implemented by a model engine comprising a memory storing instructions and a processor to execute the instructions , wherein the method comprises:receiving data of a target object, wherein the data comprises a capability parameter of the target object, wherein the capability parameter comprises a measured capability parameter and a statistical capability parameter that correspond to the target object;generating a growing model capability parameter matrix of the target object, wherein the growing model capability parameter matrix comprises the capability parameter, capability parameter adjustment value, and a comprehensive capability parameter that are each based on the capability parameter;adjusting the capability parameter adjustment value in the growing model capability parameter matrix to determine an adjusted capability parameter adjustment value, wherein the comprehensive capability parameter and the capability parameter adjustment value are based on a formula that uses the capability parameter;determining whether the adjusted capability parameter ...

WARNING SYSTEM, WARNING METHOD, AND COMPUTER PROGRAM PRODUCT

A warning system according to an embodiment includes an acquisition unit, an analysis unit, and a calculation unit. The acquisition unit acquires, from first sensor data including information on a target, condition information on the target. The analysis unit analyzes, from second sensor data including information on a region, current state information on an object included in the region and action prediction information on the object. The calculation unit calculates a degree of caution, based on the condition information on the target, the current state information on the object, and the action prediction information on the object. 1. A warning system comprising: an acquisition unit configured to acquire, from first sensor data including information on a target, condition information on the target;', 'an analysis unit configured to analyze, from second sensor data including information on a region, current state information on an object included in the region and action prediction information on the object; and', 'a calculation unit configured to calculate a degree of caution, based on the condition information on the target, the current state information on the object, and the action prediction information on the object., 'a hardware processor configured to function as2. The warning system according to claim 1 , whereinin a case where it is identified from the condition information on the target that the target is in operation or in motion, the calculation unit calculates the degree of caution higher as the object is more likely to approach or come in contact with the target, based on the current state information on the object and the action prediction information on the object.3. The warning system according to claim 1 , whereinthe calculation unit determines whether or not a predetermined number of persons are at predetermined positions in predetermined states and calculates, in a case where the predetermined number of persons are not at the predetermined ...

MONITOR CONTROL SYSTEM AND DATA COLLECTION APPARATUS

A data collection apparatus includes a data collection section configured to receive sequential time-series output data pieces for each of data sources, a data shaping section configured to perform data shaping processing on the sequential time-series output data pieces based on a predetermined data shaping rule set for each of the data sources such that the resulting data pieces are reduced in number or in data amount as compared with the output data pieces output from the data source, a data transmission section configured to transmit the output data pieces to the monitor control apparatus, and a data shaping rule control section configured to receive the data shaping rule set for each of the data sources from the monitor control apparatus and to set the received data shaping rule in the data shaping section. 1. A monitor control system comprising a monitor control apparatus configured to detect a phenomenon leading to a particular result based on output data pieces output from a plurality of data sources serving as data transmission elements and a data collection apparatus configured to collect the output data pieces and to transmit the collected output data pieces to the monitor control apparatus over a network ,wherein the data collection apparatus includes:a data collection section configured to receive sequential time-series output data pieces output from the data source for each of the plurality of data sources;a data shaping section configured to process the sequential time-series output data pieces for each of the data sources based on a predetermined data shaping rule set for each of the data sources to perform data shaping processing on the sequential time-series output data pieces such that the resulting data pieces are reduced in number as compared with the output data pieces output from the data source or in data amount as compared with the output data pieces output from the data source;a data transmission section configured to transmit the output ...

SYSTEM AND METHOD FOR VIRTUAL ENERGY ASSESSMENT OF FACILITIES

Embodiments of the invention provide methods and systems to analyze energy consumption and support demand management of a portfolio of facilities. Some embodiments of the invention include a computer implemented method for collecting and cleansing street addresses, time series energy consumption and weather data, classifying energy end-use types, detecting energy related characteristics, creating facility energy models, estimating energy savings potentials and generating customized recommendations for facilities. In some embodiments, the computer-implemented system and method also prioritizes a portfolio of facilities at each stage of the analysis based on facility data quality, level of confidence and energy savings potentials. 1. A computer-implemented system for remotely assessing energy performance of a plurality of facilities , the system comprising:a processor;a non-transitory computer-readable storage medium in data communication with the processor, the non-transitory computer-readable storage medium including steps executable by the processor for assessing the energy performance, and configured to:store locations of the facilities in the non-transitory computer-readable storage medium;store in the non-transitory computer-readable storage medium a time series of facility energy use values at desired interval sizes for usage energy transference media comprising at least one of electricity, natural gas, steam, hot water, chilled water or fuel oil;store corresponding outdoor weather values including at least one of dry/wet bulb temperature, humidity, wind speed, cloud coverage, sunrise/sunset time or solar radiation for the same time series periods in the non-transitory computer-readable storage medium;detect and condition outliers of energy use values using the processor;classify facility use types based on at least one of facility asset data, tax assessor data, search engine results, or energy time series data patterns using the processor;detect and quantify ...

SYSTEMS AND METHODS FOR IMPROVED OPERATIONS OF SKI LIFTS

Systems and methods for improved operations of ski lifts increase skier safety at on-boarding and off-boarding locations by providing an always-on, always-alert system that “watches” these locations, identifies developing problem situations, and initiates mitigation actions. One or more video cameras feed live video to a video processing module. The video processing module feeds resulting sequences of images to an artificial intelligence (AI) engine. The AI engine makes an inference regarding existence of a potential problem situation based on the sequence of images. This inference is fed to an inference processing module, which determines if the inference processing module should send an alert or interact with the lift motor controller to slow or stop the lift. 121-. (canceled)22. A computerized method for improved ski lift operations , comprising:capturing, by at least one computer processor, digital video of one or more of on-boarding and off-boarding operations of a ski lift;generating, by at least one computer processor, as the ski lift is operating, a plurality of digital images of the one or more of on-boarding and off-boarding operations of the ski lift based on the captured digital video, wherein the plurality of digital images includes sequences of video frames, wherein each sequence of the sequences of video frames includes a plurality of individual video frames representing a sequence of events;automatically detecting, by at least one computer processor, in real-time as the digital video is being captured, as the ski lift is operating, a potential problem situation represented by an abnormal position of a lift rider while on-boarding or off-boarding the ski lift in one or more of an on-boarding area and an off-boarding area of the ski lift based on the plurality of digital images, wherein the automatically detecting the potential problem situation includes:determining, based on a combined sequence of video frames of at least one of the sequences of video ...

METHOD AND DEVICE FOR DETERMINING AT LEAST ONE STATE VARIABLE OF A STORAGE ELEMENT FOR ELECTRICAL ENERGY

A method and an apparatus for determining at least one state variable of a storage element for electrical energy having at least one control device, at least one storage element for electrical energy, and at least one temperature sensor, wherein the temperature sensor detects the temperature of the storage element continuously or periodically, wherein the control device determines the state variable of the storage element at least based on the detected temperature, wherein the control device fills measurement gaps of the temperature sensor using data of a weather service, the data then is used in the determination of the at least one state variable. 1. A method for determining at least one state variable of a storage element for electrical energy , the method comprising:continuously or periodically detecting a temperature of the storage element by a temperature sensor;determining the state variable at least based on the temperature of the storage element; andfilling measurement gaps of the temperature sensor using weather service temperature data to make the determination of the at least one state variable.2. The method of claim 1 , wherein the state variable is state of health of the storage element.3. The method of claim 1 , wherein the weather service data are provided by a server that processes data of at least one weather service.4. The method of claim 1 , further comprising applying a correction factor to the weather service temperature data claim 1 , the correction factor being dependent at least on cloud cover and/or a position of the sun.5. The method of claim 1 , further comprising generating a warning signal depending on the determined state variable.6. An apparatus for determining at least one state variable of a storage element for electrical energy claim 1 , the apparatus comprising:at least one control device;at least one storage element for electrical energy; andat least one temperature sensor,wherein the at least one temperature sensor detects the ...

OPERATING MODE DETERMINING METHOD AND OPERATING MODE DETERMINING DEVICE

Disclosed are an operating mode determining method and an operating mode determining device for determining an operating mode of a clothing treatment apparatus using image information by executing an artificial intelligence (AI) algorithm and/or machine learning algorithm in a 5G environment connected for the Internet of Things. According to an embodiment of the present disclosure, the operating mode determining method includes obtaining first image information obtained by photographing clothing through a camera of the clothing treatment apparatus, obtaining second image information obtained by photographing an entrance and exit of a user wearing the clothing through a camera for monitoring an entrance and exit of a room, and determining an operating mode of the clothing treatment apparatus according to an analysis result of the first image information and the second image information. 1. A method of controlling an operation of a clothing treatment apparatus installed indoors , the method comprising:obtaining first image information obtained by photographing clothing through a camera of the clothing treatment apparatus;obtaining second image information obtained by photographing an entrance and exit of a user wearing the clothing through a camera for monitoring an entrance and exit of a room; anddetermining an operating mode of the clothing treatment apparatus according to an analysis result of the first image information and the second image information.2. The method of claim 1 , wherein the obtaining of the second image information comprises obtaining the second image information including a going out time and a returning time of the user wearing the clothing.3. The method of claim 2 , further comprising claim 2 , after the obtaining of the second image information and before the determining of the operating mode claim 2 , obtaining location information between the going out time and the returning time from the user's terminal.4. The method of claim 2 , wherein ...

Control device, control system, control method and program

A prediction value calculator calculates a prediction value of an electricity fee based on the amount of electric power supplied from a commercial electric power source to electric equipment within an electricity fee calculation period. A selector selects, as a first-stage control, either one control of an electric power saving control for the electric equipment and a charge-discharge control in which the electric power supplied from the commercial electric power source is stored in a storage battery in a first time slot and the electric power stored in the storage battery is supplied to the electric equipment in a second time slot in which the unit cost of the electric power supplied from the commercial electric power source is greater than that in the first time slot. A controller executes the first-stage control selected by the selector when the prediction value calculated by the prediction value calculator is greater than a targeted value of the electricity fee.

BUILDING CONTROL SYSTEM WITH ADAPTIVE ONLINE SYSTEM IDENTIFICATION

A controller for equipment that operates to affect a variable state or condition of a building including one or more processors and non-transitory computer-readable media storing instructions that, when executed by the processors, cause the processors to perform operations. The operations include generating a new predictive model using training data associated with one or more durations selected from a time period and selected to satisfy a set of criteria. The predictive model models system dynamics of the building during the time period. The operations include storing the new predictive model in a database including predictive models that model the system dynamics of the building and include comparing performance of the new predictive model and the predictive models stored by the database to select a particular predictive model for controlling the equipment. The operations include using the particular predictive model to generate and provide control signals to the equipment. 1. A controller for equipment that operates to affect a variable state or condition of a building , the controller comprising:one or more processors; and generating a new predictive model using training data associated with system dynamics of the building and one or more durations selected from a time period, the new predictive model modeling the system dynamics of the building, the one or more durations selected to satisfy a set of criteria;', 'storing the new predictive model in a database comprising a plurality of predictive models that model the system dynamics of the building;', 'comparing performance of the new predictive model and the plurality of predictive models stored by the database to select a particular predictive model for controlling the equipment; and', 'using the particular predictive model to generate and provide control signals to the equipment., 'one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause ...

ENVIRONMENT MONITORING AND MANAGEMENT SYSTEMS AND METHODS

A method for managing air quality may include, at one or more processors, receiving sensor data comprising a plurality of air quality parameters for an environment, wherein the sensor data is generated by one or more environment quality monitoring devices located in the environment, predicting an adverse air quality event based on the sensor data, and automatically controlling one or more devices to mitigate the adverse air quality event. An environment quality monitoring device may include a housing, a plurality of sensors in the housing and configured to generate sensor data comprising a plurality of environment quality parameters, a network communication device configured to communicate the sensor data over a network, and an alert configured to indicate an environment quality score of the ambient environment, where the environment quality score is based on at least a portion of the sensor data. 1. A method for managing air quality , comprising:at one or more processors:receiving sensor data comprising a plurality of air quality parameters for an environment, wherein the sensor data is generated by one or more environment quality monitoring devices located in the environment;predicting an adverse air quality event based on the sensor data; andautomatically controlling one or more devices to mitigate the adverse air quality event.2. The method of claim 1 , wherein the plurality of air quality parameters comprises an amount of particulate matter in the environment.3. The method of claim 2 , wherein the adverse air quality event comprises an amount of particulate matter above a predetermined threshold level claim 2 , and wherein automatically controlling one or more devices to mitigate the adverse air quality event comprises automatically activating one or more air filtering devices.4. The method of claim 1 , wherein the plurality of air quality parameters comprises an amount of a gas in the environment.5. The method of claim 4 , wherein the gas comprises at least ...

METHOD FOR GENERATING SCHEDULE DATA BASED ON ACTION DATA, AND SERVER AND REFRIGERATOR FOR IMPLEMENTING THE SAME

Disclosed herein is a method for generating schedule data based on action data, and a server and a refrigerator implementing the same. The method for generating schedule data based on action data according to an embodiment of the present invention includes, in a refrigerator including one or more divided storage spaces, a step of a storage unit of the refrigerator storing pattern base data including action data performed by the refrigerator and time data, a step of a communication unit of the refrigerator receiving a first learning data set from a server, a step of a schedule generation unit of the refrigerator generating first schedule data including predicted action data of the refrigerator and time data of the predicted action data by mapping a first learning data set to the pattern base data, and a step of a control unit of the refrigerator controlling an action of the refrigerator based on the first schedule data. 1. A method for generating operation schedule data for a refrigerator , the method comprising:storing, in a storage unit of the refrigerator, first usage storing pattern base data that includes operation data performed by the refrigerator or a user and time data corresponding to the operation data;receiving, by a communication unit of the refrigerator, a first learning data set from a server;generating first operation schedule data during a first prediction unit period, the first operation schedule data including first predicted usage data of the refrigerator and first predicted time data corresponding to the first predicted usage data, wherein generating the first operation schedule data comprises mapping the first learning data set to the first usage pattern base data; andcontrolling, by a control unit of the refrigerator, operation of the refrigerator based on the first operation schedule data.2. The method of claim 1 , further comprising:transmitting, by the communication unit, second usage pattern base data generated during an upload unit period ...

SECURITY EVENT DETECTION WITH SMART WINDOWS

Optically controllable windows and an associated window control system provide a building security platform. A window controller or other processing device can monitor for window breakage, cameras associated with windows can monitor for intruders, and transparent displays can provide alerts regarding detected activity within a building. A window control system can detect deviations from expected UV characteristics of an optically controllable window during normal operation of the window (tint transitions, steady state conditions, etc.) and/or during application of a security-related perturbing event, and provide alerts upon their occurrence. 1. A method of detecting a security-related event in an optically switchable window , the method comprising:(a) measuring a current or voltage of an optically switchable device of the optically switchable window without perturbing a process of driving a transition between optical states and/or maintaining an end optical state of the optically switchable window;(b) evaluating the current or voltage measured in (a) to determine whether the current or voltage measured in (a) indicates that the optically switchable window is broken or damaged; and(c) in response to detecting the response in (b), performing a security action.2. The method of claim 1 , wherein measuring the current or voltage of the optically switchable device is performed while the optically switchable window is undergoing the transition from a first tint state to a second tint state.3. The method of claim 1 , wherein measuring the current or voltage of the optically switchable device includes measuring an open circuit voltage of the optically switchable device.4. The method of claim 3 , wherein measuring the open circuit voltage of the optically switchable device is performed while the optically switchable window is undergoing the transition from a first tint state to a second tint state.5. The method of claim 1 , wherein evaluating the current or voltage measured ...

INFORMATION PROCESSING DEVICE AND INFORMATION PROCESSING METHOD

[Problem] To achieve an optimum operation following purpose change. 1. An information processing device comprising an action value calculation unit configured to calculate an action value that determines behavior of an operation unit , whereinbased on an acquired purpose change factor and a plurality of first action values learned based on rewards different from each other, the action value calculation unit dynamically calculates a second action value to be input to the operation unit.2. The information processing device according to claim 1 , wherein the action value calculation unit dynamically calculates a plurality of the second action values based on ratios determined based on the purpose change factor.3. The information processing device according to claim 1 , wherein the action value calculation unit dynamically calculates the second action value by summing a plurality of the first action values claim 1 , based on weights of the first action values determined based on the purpose change factor.4. The information processing device according to claim 1 , wherein the purpose change factor includes a purpose change instruction provided by a user.5. The information processing device according to claim 1 , wherein the purpose change factor includes change in an operation environment of the operation unit.6. The information processing device according to claim 5 , wherein the purpose change factor includes matching of the operation environment with a predetermined environment estimated from context.7. The information processing device according to claim 5 , wherein the purpose change factor includes matching of the operation environment with a predetermined environment in which a user sets a purpose operation.8. The information processing device according to claim 1 , further comprising an operation unit configured to dynamically change behavior based on the second action value and an estimated operation environment.9. The information processing device according to ...

PATH DEVIATION DETECTION ANALYSIS BY PATTERN RECOGNITION ON SURFACES VIA MACHINE LEARNING

An approach for analyzing and predicting a pattern of debris accumulation in area based on a deviation in mobility pattern. The approach includes receiving data from one or more sensors from an area and identifying objects based on the received data. The approach determines whether the received data is a first instance and stores the data. Based on the stored data, the approach analyzes, via machine learning, a mobility pattern associated with the retrieved data. Furthermore, the approach generates an actionable task list based on the analyzed data and instructs one or more computing devices based on the actionable task list 1. A computer-implemented method of detecting and predicting mobility pattern , the method comprising:receiving, by one or more computer processors, data from one or more sensors from an area;identifying, by the one or more computer processors, objects based on the received data;determining, by the one or more computer processors, whether the received data is a first instance;responsive to determining that the received data is not the first instance, analyzing, by the one or more computer processors, via machine learning, a mobility pattern associated with the retrieved data;generating, by the one or more computer processors, an actionable task list based on the analyzed data, wherein the analyzed data comprises a deviation in the mobility pattern; andinstructing, by the one or more computer processors, one or more computing devices based on the actionable task list.2. The computer-implemented method of claim 1 , wherein the one or more sensors comprises of IoT devices claim 1 , drones claim 1 , cleaning robots and mobile computing devices.3. The computer-implemented method of claim 1 , wherein the identified objects based on the received data comprises of pedestrian and vehicle traffic.4. The computer-implemented method of claim 1 , wherein analyzing a mobility pattern associated with the retrieved data comprises of claim 1 , but is not limited ...

ROBOTIC SURGICAL SYSTEM AND METHOD FOR CONFIGURING A SURGICAL ROBOT

A robotic surgical system for treating a patient includes a surgical robot with a moveable robot member, an actuator for moving the robot member to 6D poses in a surgical field and for driving the robot member to act in the surgical field, a robot sensor for providing robot sensor data, and a control device for controlling the actuator according to a control program and under feedback of the robot sensor data, a processing unit configured to provide the control program to the control device, and to include and utilize a virtual anatomical model, a virtual surgical robot simulating movement and driving of the robot member, a surgical simulator, a sensor simulator, and a machine learning unit to create the control program, the machine learning unit reading the sensor simulator, the virtual surgical robot, and the virtual surgical field and feeding the virtual surgical robot. 1. A robotic surgical system for treating a patient , the robotic surgical system comprising:a surgical robot comprising a moveable robot member;at least one actuator configured to move the moveable robot member to 6D poses in a surgical field and to drive the moveable robot member to act in the surgical field;at least one robot sensor configured to provide robot sensor data giving the at least one actuator a feedback signal and depending on conditions in the surgical field; anda control device configured to control the at least one actuator according to a control program and under feedback of the robot sensor data; anda processing unit configured to provide the control program to the control device, wherein the processing unit is further configured to comprise:a virtual anatomical model providing a virtual surgical field;a virtual surgical robot simulating a movement and driving of the moveable robot member;a surgical simulator reading the virtual anatomical model and reading the virtual surgical robot regarding the movement and the driving of the moveable robot member;a sensor simulator creating ...

TOLERANCE-BASED INTELLIGENT EDGE NETWORK ENERGY DELIVERY

Systems and techniques for tolerance-based intelligent edge network energy delivery are described herein. A flexibility metric may be calculated for a node of the edge network. The flexibility metric of the node and flexibility metrics of a set of additional nodes of the edge network may be ranked to create a set of flexibility ranked edge nodes. A notification may be received of a demand response event. A candidate node subset may be identified from the set of flexibility ranked nodes based on requirements of the demand response event and a ranked order the set of flexibility ranked nodes. A demand response command may be transmitted to the candidate node subset upon determining that the candidate node subset satisfies the requirements of the demand response event. The demand response command may cause nodes of the candidate node subset to alter energy consumption for a time period of demand response event. 1. A system for tolerance-based intelligent energy delivery at an edge network , the system comprising:at least one processor; and calculate a flexibility metric for a node of the edge network;', 'receive a notification of a demand response event from a utility service communicatively coupled to the edge network;', 'identify a candidate node subset from a set of flexibility-ranked nodes based on requirements of the demand response event and a ranked order of the set of flexibility-ranked nodes; the set of flexibility-ranked nodes including the node; and', 'transmit a demand response command to the candidate node subset upon a determination that the candidate node subset satisfies the requirements of the demand response event, wherein the demand response command causes nodes of the candidate node subset to alter energy consumption for a time period coinciding with the demand response event., 'memory including instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to2. The system of claim 1 , wherein ...

Method and System of Collecting Training Data Suitable for Training an Autonomous Driving System of a Vehicle

The present disclosure enables a collection of training data suitable for training an autonomous driving system of a vehicle. A database is provided that stores predefined road scenarios, and user devices are provided with a simulation game for controlling a vehicle agent in a road scenario. A plurality of user devices, running the simulation game, play a road scenario from the database to control a vehicle agent in the simulation game with steering actions entered by individual users, which generates a human demonstration of each road scenario that is played. Several human demonstrations played on the plurality of user devices can be maintained by a demonstration database and made available as training data suitable for training an autonomous driving system of a vehicle. A large amount of training data can be automatically generated, without requiring expensive or time-consuming real-world tests to generate suitable training data manually. 1. A method , comprising: providing a scenario database storing predefined road scenarios;', 'providing user devices with a simulation game for controlling a vehicle agent in a road scenario;', 'at each of a plurality of user devices, running the simulation game, playing a road scenario from the scenario database on a display of the user device, controlling the vehicle agent in the simulation with steering actions entered by a user of the user device, and generating a human demonstration of the played road scenario;', 'collecting, as training data, a plurality of human demonstrations of the stored road scenarios played on the plurality of user devices; and', 'storing, by at least one processor, the training data in a demonstration database that is accessible to the vehicle for training the autonomous driving system to handle controlling the vehicle in a driving situation related to at least one simulated road scenario from the scenario database., 'collecting training data suitable for training an autonomous driving system of a ...

System And Apparatus For Integrated HVACR And Other Energy Efficiency And Demand Response

Electronic controller apparatus for automatically controlling and managing load demand and operation of energy-consuming equipment powered by alternating electrical power current, whereby feedback signals from a vapor compression evaporator or other source, and possibly other physical signals, are used to supplement the pre-fixed, learned, or default settings to optimize compressor operation (run time) in cooling and refrigeration equipment, and thereby to improve heat transfer in the evaporator. The effect is to improve the Energy Efficiency Ratio (EER), Seasonal Energy Efficiency Ratio (SEER), and Coefficient of Performance (COP) for the unit, and provide other advantages and improvements. In gas-, oil-, and propane-fired HVAC&R heating systems, the apparatus can also optimize burner operation and thereby improve heat transfer across the burner heat exchanger. HVAC&R systems that incorporate the demand controller and methods of their operation also are provided. The apparatus can also be applied to gas compression and compressed air control systems. 1. An electronic controller apparatus for automatically controlling and managing load demand and operation of energy-consuming equipment powered by alternating electrical power current , comprising:a) a controller switch connectible in series with a control signal line that connects with a load unit control switch that controls flow of operative power to a load unit, and the controller switch capable to open and close the control signal line;b) a digital recycle counter comprising a counter for generating a count of oscillations of an oscillating control signal in the control signal line, and capable for defining an elapsed run time interval and an elapsed idle time interval for the load unit;c) a digital timer for providing an input index of real time, and capable of defining an elapsed run time interval and an elapsed idle time interval for the load unit;d) a learning module for analysis of input information and ...

Systems and Related Apparatus for Improving Process Data Integrity and Timeliness

Systems, apparatus, and methods for improving the monitoring of processes. These systems comprise processors co-located with the (physical) processes and which accept certain metrics regarding the processes. These systems also include processors which are located remotely from the processes, but, which are in communication with the co-located processors. The remote processors receive the metrics from the co-located processors and transform these metrics to corresponding probability metrics. Based on the probability metrics, the remote processors determine whether the processes are predictable. They also output the predictability determinations regarding the processes. The processes can be associated with petrochemical wells, food/beverage processes, etc. Additionally, or in the alternative, some systems further comprise memories which store flowchart representations of the processes. In various embodiments, the remote processors associate the metrics with the operations represented in the flowcharts. 1. A system for monitoring a physical process , the system comprising:a processor co-located with the physical process and being configured to accept a safety-related metric regarding the physical process;a network in communication with the co-located processor;a processor located remotely from the physical process and in communication with the network, the remote processor being configured to receive the safety-related metric regarding the physical process from the co-located processor, to transform the safety-related metric regarding the physical process to a probability metric, and to determine, based on the probability metric, whether the physical process is predictable; andan output device in communication with the remote processor wherein the remote processor is further configured to output the safety-related predictability determination regarding the physical process via the output device.2. The system of wherein the physical process is associated with a ...

A METHOD FOR OPERATING A THERMAL SYSTEM AND A THERMAL SYSTEM

A method for operating a thermal system, wherein a component of a facility or building has to be heated and/or cooled by the thermal system, includes selecting a control mode of the thermal system for bringing and/or maintaining the component to or at a definable temperature value or to or within a definable temperature value range. The control mode is dynamically selected from multiple different control modes under consideration of at least one boundary condition of the component and/or at least one environmental context parameter and under consideration of data regarding learnt/adapted thermal behaviour of the component. 1. A method for operating a thermal system , wherein a component of a facility or building has to be heated and/or cooled by the they system , the method comprising:selecting a control mode of the thermal system for bringing and/or maintaining the component to or at a definable temperature value or to or within a definable temperature value range,wherein the control mode is dynamically selected from multiple different control modes under consideration of at least one boundary condition of the component and/or at least one environmental context parameter and under consideration of data regarding learnt/adapted thermal behaviour of the component.2. The method according to claim 1 , wherein the control mode is dynamically selected in real-time.3. The method according to claim 1 , wherein a real-time monitoring of the at least one environmental context parameter and/or of at least one system parameter and/or component parameter and/or subsystem parameter is performed during operation of the thermal system.4. The method according to claim 1 , wherein the data regarding the learnt/adapted thermal behaviour of the component is based on historic data and operational data monitored during operation of the thermal system.5. The method according to claim 1 , wherein the data regarding the learnt/adapted thermal behaviour of the component is dynamically ...

System modeling, control and optimization

A method for modeling an operation of a system that may include a disturbance rejection model that is configured to generate a predicted value for a system output at a future time. The disturbance rejection model may include a neural network for mapping system inputs to the system output. The method may include the steps of: training the disturbance rejection model per a training dataset; and calculating a confidence metric for the disturbance rejection model. The confidence metric is configured to indicate a probability that a predicted sign of a gain in the system output at the future time made by the disturbance rejection model is correct.

Model generating method and apparatus

An embodiment of the present invention relates to a model generating method and apparatus, for realizing automatic creation of a system model. A model generating method of an embodiment includes: collecting configuration information of a system; extracting semantic description information from the configuration information; generating a model of the system according to the semantic description information, the model of the system including a relationship between model nodes and the model nodes corresponding to a device in the system or data produced by a device in the system. By extracting semantic description information from configuration information to generate a system model, a method for realizing automatic creation of a system model is provided, giving higher precision than manual creation of a system model.

SYSTEM MODELING, CONTROL AND OPTIMIZATION

A method for training a disturbance rejection model that is configured to model an operation of a system so to calculate a predicted value for a system output at a future time. The disturbance rejection model may include a network for mapping system inputs to the system output, the network including a weight vector and a feedback coefficient. The method may include: obtaining a training dataset, and training the disturbance rejection model pursuant to the training dataset. The training may include calculating updated values for each of the weight vector and the feedback coefficient of the network by minimizing an error function that include a first hyperparameter and a second hyperparameter. The first hyperparameter may include a vector for penalizing the weight vector and the second hyperparameter may include a scalar. 2. The method of claim 1 , wherein the disturbance rejection model comprises a disturbance rejection configuration in which the predicted value made by the disturbance rejection model for the system output at the future time is based upon: a predicted value made by the network for the system output at the future time; and a value of a bias claim 1 , the bias being based upon the feedback coefficient and an error;wherein the network comprises a neural network that includes multiple layers having nodes, the multiple layers including at least an input layer, an output layer, one or more hidden layers, and forward weight matrixes; and the input layer comprises a plurality of the nodes, the plurality of the nodes corresponding respectively to the system inputs, wherein each of the plurality of the nodes is configured to receive an input signal relating to a value for a particular one of the system inputs;', 'the output layer comprises at least one of the nodes, the at least one of the nodes corresponding to the system output;', 'the one or more hidden layers are disposed between the input layer and the output layer, each of the one or more hidden layers ...

ERROR CORRECTION FOR PREDICTIVE SCHEDULES FOR A THERMOSTAT

A heating, ventilation, and air conditioning (HVAC) control device is configured to record a plurality of actual occupancy statuses, to determine a plurality of corresponding predicted occupancy statuses, and to compare the plurality of predicted occupancy statuses to the plurality of actual occupancy statuses. The device is further configured to identify conflicting occupancy statuses based on the comparison. A conflicting occupancy status indicates a difference between an actual occupancy status and a corresponding predicted occupancy status. The device is further configured to identify timestamps corresponding with the conflicting occupancy statuses, to identify historical occupancy statuses corresponding with the identified timestamps, and to update the conflicting occupancy statuses in the predicted occupancy schedule with the historical occupancy statuses. 1. A heating , ventilation , and air conditioning (HVAC) control device , comprising: [ each time entry corresponds with a day of a week and an hour of a day; and', 'each time entry is associated with a predicted occupancy status; and, 'a predicted occupancy schedule comprising a plurality of time entries, wherein, 'an occupancy history log comprising a plurality of historical occupancy statuses, wherein each historical occupancy status is associated with a timestamp corresponding with a day and an hour of a day over a first period of time; and, 'a memory operable to store record a plurality of actual occupancy statuses, wherein each actual occupancy status is associated with a timestamp corresponding with a day and an hour of a day over a second period of time;', 'determine a plurality of predicted occupancy statuses, wherein each predicted occupancy status corresponds with a timestamp of an actual occupancy status;', 'compare the plurality of predicted occupancy statuses to the plurality of actual occupancy statuses;', 'identify one or more conflicting occupancy statuses based on the comparison, wherein a ...

ERROR CORRECTION FOR PREDICTIVE SCHEDULES FOR A THERMOSTAT

A heating, ventilation, and air conditioning (HVAC) control device is configured to record a plurality of actual occupancy statuses, to determine a plurality of corresponding predicted occupancy statuses, and to compare the plurality of predicted occupancy statuses to the plurality of actual occupancy statuses. The device is further configured to identify conflicting occupancy statuses based on the comparison. A conflicting occupancy status indicates a difference between an actual occupancy status and a corresponding predicted occupancy status. The device is further configured to identify timestamps corresponding with the conflicting occupancy statuses, to identify historical occupancy statuses corresponding with the identified timestamps, and to update the conflicting occupancy statuses in the predicted occupancy schedule with the historical occupancy statuses. 1. A heating , ventilation , and air conditioning (HVAC) control device , comprising: [ each time entry corresponds with a day of a week and an hour of a day; and', 'each time entry is associated with a predicted occupancy status; and, 'a predicted occupancy schedule comprising a plurality of time entries, wherein, 'an occupancy history log comprising a plurality of historical occupancy statuses, wherein each historical occupancy status is associated with a timestamp corresponding with a day and an hour of a day over a first period of time; and, 'a memory operable to store record a plurality of actual occupancy statuses, wherein each actual occupancy status is associated with a timestamp corresponding with a day and an hour of a day over a second period of time;', 'determine a plurality of predicted occupancy statuses, wherein each predicted occupancy status corresponds with a timestamp of an actual occupancy status;', 'compare the plurality of predicted occupancy statuses to the plurality of actual occupancy statuses;', 'identify one or more conflicting occupancy statuses based on the comparison, wherein a ...

TECHNOLOGIES FOR PREDICTING POWER USAGE OF A DATA CENTER

Technologies for predicting the power usage of a data center are disclosed. A data center manager gathers sensor data from the compute devices of the data center. The sensor data indicates factors such as power used by the compute device and the intake air inlet temperature. The data center manager trains a machine-learning-based algorithm based on training sensor data, and then applies the machine-learning-based algorithm to sensor data as it is being gathered. The machine-learning-based algorithm can predict a change in future power usage of the data center, and control a cooling unit to compensate before the power usage even begins to change. 1. A data center manager for prediction of power usage of a data center , the data center manager comprising:one or more processors; receive sensor data from one or more sensors from one or more sleds of the data center;', 'acquire one or more sensor data samples based on the sensor data;', 'acquire one or more parameters of a machine-learning-based algorithm;', 'predict, based on the one or more sensor data samples, a future power usage of the data center with use of the one or more parameters of the machine-learning-based algorithm; and', 'control at least one cooling unit of the data center based on the predicted future power usage., 'one or more memory devices having stored therein a plurality of instructions that, when executed by the one or more processors, causes the data center manager to2. The data center manager of claim 1 , wherein to acquire one or more sensor data samples based on the sensor data comprises to:average, for each of the one or more sensors, the corresponding sensor data over a period of time;calculate, for at least one sensor of the one or more sensors, a moving average convergence/divergence (MACD) of the corresponding sensor data;calculate, for at least one sensor of the one or more sensors, a bias of the corresponding sensor data; andgenerate the one or more sensor data samples based on the ...

ENVIRONMENT CONTROL SYSTEM

An environment control system that controls an environment of a subject is provided. The environment control system includes an actuator configured to control an environment of a subject, and a controller configured to control an operation of the actuator. The environment control system includes an inference unit that includes a first learned model and a second learned model. The first learned model has been trained by associating environmental information indicating an environment of a subject with data correlating with one of sleep, excretion, movement, skin, and stress conditions of the subject. The second learned model has been trained by associating the data correlating with one of the sleep, excretion, movement, skin, and stress conditions of the subject with data correlating with a magnitude of one or more risks that may occur with respect to the subject in a future period of time. The environment control system includes an operating condition determining unit configured to, in a case in which data correlating with the magnitude of the one or more risks that may occur with respect to a subject in a future period of time is inferred based on the first and second learned model, evaluate the inferred data to determine an operating condition of the actuator. 1. An environment control system for controlling an environment of a subject , comprising:an actuator configured to control an environment;an operating condition determining unit configured to determine an operating condition of the actuator;a controller configured to control the actuator based on the operating condition determined by the operating condition determining unit; andan inference unit that includes a first learned model and a second learned model,wherein the first learned model is a model that has been trained by associating environmental information indicating an environment of a subject with data correlating with at least one of sleep, excretion, movement, skin, and stress conditions of the ...

HVAC SYSTEM INCLUDING ENERGY ANALYTICS ENGINE

A heating, ventilation, and air conditioning (HVAC) energy management control system includes an HVAC system configured to deliver at least one of heated air and cooled air to a targeted area; and a computing server including an HVAC energy analytics engine in signal communication with the HVAC system. The HVAC energy analytics engine is configured to actively learn historical data of the HVAC system based on at least one of the heated air and the cooled air produced over a time period. The HVAC energy analytics engine determines a predicted energy consumption of the HVAC system based on the historical data, and the HVAC system operates based on the predicted energy consumption. 1. A heating , ventilation , and air conditioning (HVAC) energy management control system comprising:an HVAC system configured to deliver at least one of heated air and cooled air to a targeted area; anda computing server including an HVAC energy analytics engine in signal communication with the HVAC system, the HVAC energy analytics engine configured to actively learn historical data of the HVAC system based on at least one of the heated air and the cooled air produced over a time period,wherein the HVAC energy analytics engine determines a predicted energy consumption of the HVAC system based on the historical data, and the HVAC system operates based on the predicted energy consumption.2. The system of claim 1 , further comprising at least one electronic terminal device in signal communication with the computing server claim 1 , the at least one electronic terminal device configured to deliver at least one HVAC unit characteristic to the HVAC energy analytics engine.3. The system of claim 2 , wherein the HVAC system includes an HVAC unit that generates the heated air and the cooled air claim 2 , and an HVAC controller that is configured to receive a temperature set point value claim 2 , and to control the HVAC unit based on a temperature set point value.4. The system of claim 3 , wherein ...

DEEP LEARNING-BASED REAL-TIME DETECTION AND CORRECTION OF COMPROMISED SENSORS IN AUTONOMOUS MACHINES

A mechanism is described for facilitating deep learning-based real-time detection and correction of compromised sensors in autonomous machines according to one embodiment. An apparatus of embodiments, as described herein, includes detection and capturing logic to facilitate one or more sensors to capture one or more images of a scene, where an image of the one or more images is determined to be unclear, where the one or more sensors include one or more cameras. The apparatus further comprises classification and prediction logic to facilitate a deep learning model to identify, in real-time, a sensor associated with the image. 1. An apparatus comprising:detection and capturing logic to facilitate one or more sensors to capture one or more images of a scene, wherein an image of the one or more images is determined to be unclear, wherein the one or more sensors include one or more cameras; andclassification and prediction logic to facilitate a deep learning model to identify, in real-time, a sensor associated with the image.2. The apparatus of claim 1 , further comprising concatenation logic to receive one or more data inputs associated with the one or more images to concatenate the one or more data inputs into a single data input to be processed by the deep learning model claim 1 , wherein the apparatus comprises an autonomous machine includes one or more of a self-driving vehicle claim 1 , a self-flying vehicle claim 1 , a self-sailing vehicle claim 1 , and an autonomous household device.3. The apparatus of claim 1 , further comprising training and inference logic to facilitate the deep learning model to receive the single data input to perform one or more deep learning processes including a training process and an inferencing process to obtain real-time identification of the sensor associated with the unclear image claim 1 , wherein the sensor includes a camera.4. The apparatus of claim 3 , wherein the training and inferencing logic is further to facilitate the deep ...

SYSTEM IDENTIFICATION AND MODEL DEVELOPMENT

A controller for a building system receives training data including input data and output data. The output data indicate a state of the building system affected by the input data. The controller pre-processes the training data using a first set of pre-processing options to generate a first set of training data and pre-processes the training data using a second set of pre-processing options to generate a second set of training data. The controller performs a multi-stage optimization process to identify multiple different sets of model parameters of a dynamic model for the building system. The multi-stage optimization process includes a first stage in which the controller uses the first set of training data to identify a first set of model parameters and a second stage in which the controller uses the second set of training data to identify a second set of model parameters. The controller uses the dynamic model to operate the building system. 2. The controller of claim 1 , wherein:the first set of the model parameters comprise system parameters; andthe second set of the model parameters comprise Kalman gain parameters.3. The controller of claim 1 , wherein:the output data is affected by both the input data and an extraneous disturbance comprising an uncontrolled input to the building system; andthe processing circuit is configured to filter the training data to remove an effect of the extraneous disturbance from the output data when performing the first pre-processing operation.4. The controller of claim 3 , wherein the extraneous disturbance comprises a slowly changing disturbance to the building system; andthe processing circuit is configured to filter the training data using a high-pass filter to remove the effect of the slowly changing disturbance from the output data when performing the first pre-processing operation.5. The controller of claim 3 , wherein:the extraneous disturbance comprises an uncontrolled thermal input to the building system;the first set of ...

SYSTEMS AND METHODS FOR INTELLIGENT PIC VALVES WITH AGENT INTERACTION

A flow control device is configured to control fluid flow in an HVAC system. The flow control device includes a valve, an actuator configured to open and close the valve, and one or more sensors. The flow control device further includes a fault detection and correction agent configured to receive data from the one or more sensors, analyze the data according to a set of rules, and detect whether one or more faults have occurred. In response to detecting a fault, the fault detection and correction agent is configured to either operate the actuator to open or close the valve or initiate a corrective action to be taken by another device in the HVAC system. 120-. (canceled)21. A flow control device configured to control fluid flow in an HVAC system , the flow control device comprising:a valve, one or more sensors, and an actuator configured to open and close the valve; and receive data from the one or more sensors;', 'analyze the data from the one or more sensors according to a set of rules; and', 'detect whether one or more faults have occurred;', 'determine whether the fault can be corrected by opening or closing the valve;', 'in response to determining the fault can be corrected by opening or closing the valve, correct the fault by operating the actuator to open or close the valve;', 'in response to determining the fault cannot be corrected by opening or closing the valve, initiate a corrective action to be taken by another device in the HVAC system., 'one or more processors configured to22. The flow control device of claim 21 , wherein the fault is a low temperature fault.23. The flow control device of claim 22 , wherein the other device in the HVAC system is a boiler and the corrective action includes operating the boiler to produce heated fluid.24. The flow control device of claim 21 , wherein the fault is a high temperature fault.25. The flow control device of claim 24 , wherein the other device in the HVAC system is a chiller and the corrective action includes ...

SMART CONTACT LENS CONTROL SYSTEM

A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor of a smart contact lens. Executing the instructions causes the smart contact lens to measure dimensions of a user's eye to determine a focal length of the user, measure a magnetic field proximate to the user's eye to determine a direction of focus of the user, receive a control input from the user, determine a control signal corresponding to the focal length of the user, the direction of focus of the user, and the received control input, generate the determined control signal, and control a first electronic device by transmitting, by the smart contact lens, the generated control signal to the first electronic device. 1. A computer program product comprising a computer readable storage medium having program instructions embodied therewith , the program instructions executable by a processor of a smart contact lens to cause the processor of the smart contact lens to:measure, by the smart contact lens, dimensions of a user's eye to determine a focal length of the user;measure, by the smart contact lens, a magnetic field proximate to the user's eye to determine a direction of focus of the user;receive, by the smart contact lens, a control input from the user;determine, by the smart contact lens, a control signal corresponding to the focal length of the user, the direction of focus of the user, and the received control input;generate, by the smart contact lens, the determined control signal; andcontrol a first electronic device by transmitting, by the smart contact lens, the generated control signal to the first electronic device.2. The computer program product of claim 1 , wherein measuring the dimensions of the user's eye comprises capturing an infrared image of the user's eye via a back-side facing camera of the smart contact lens.3. The computer program product of claim 2 , wherein executing the ...

CONTROL DEVICE AND CONTROL SYSTEM

There is provided a control device that prevents the occurrence of an abnormality in control using artificial intelligence in the case where an abnormality occurs in another terminal that performs the control using the artificial intelligence. A control means (a first control unit) performs the control using artificial intelligence. The control means (second control unit) performs control different from the artificial intelligence. A control switching unit (a switching determination means, a switch) is configured to, when another terminal having the control means (the first control unit) is normal, cause the own control means (the first control unit) to perform the control using artificial intelligence, and when an abnormality occurs in another terminal having the control means (the first control unit), cause the control means (the second control unit) to perform the control different from artificial intelligence. 1. A control device comprising:a first control unit that performs control using artificial intelligence;a second control unit that performs control different from the artificial intelligence; anda control switching unit that, when another terminal having the first control unit is normal, causes the own first control unit to perform the control using the artificial intelligence, and when an abnormality occurs in another terminal having the first control unit, causes the second control unit to perform the control different from the artificial intelligence.2. The control device according to claim 1 , comprisinga reception unit that receives an abnormality notification indicating an abnormality in the other terminal, whereinthe control switching unit is configured to,when the abnormality notification is not received, cause the first control unit to perform the control using the artificial intelligence, and when the abnormality notification is received, cause the second control unit to perform the control different from the artificial intelligence.3. The ...

CONTINUOUS CONTROL OF ATTENTION FOR A DEEP LEARNING NETWORK

A computer-implemented method for reducing computation cost associated with a machine learning task performed by a computer system by implementing continuous control of attention for a deep learning network includes initializing a control-value function, an observation-value function and a sequence of states associated with a current episode. If a current epoch associated with the current episode is odd, an observation-action is selected, the observation-action is executed to observe a partial image, and the observation-value function is updated based on the partial image and the control-value function. If the current epoch is even, a control-action is selected, the control-action is executed to obtain a reward corresponding to the control-action, and the control-value function is updated based on the reward and the observation-value function. 1. A computer-implemented method for reducing computation cost associated with a machine learning task performed by a computer system by implementing continuous control of attention for a deep learning network , comprising:initializing, by at least one processor operatively coupled to a memory device, a control-value function, an observation-value function and a sequence of states associated with a current episode; selecting, by the at least one processor, an observation-action;', 'executing, by the at least one processor, the observation-action to observe a partial image; and', 'updating, by the at least one processor, the observation-value function based on the partial image and the control-value function; and, 'if a current epoch of the current episode is odd selecting, by the at least one processor, a control-action;', 'executing, by the at least one processor, the control-action to obtain a reward corresponding to the control-action; and', 'updating, by the at least one processor, the control-value function based on the reward and the observation-value function., 'if the current epoch is even2. The method of claim 1 , ...

MACHINE LEARNING DEVICE, CONTROL DEVICE, AND MACHINE LEARNING METHOD

The settling time of machine learning is shortened. A machine learning device is configured to perform machine learning related to optimization of coefficients of a transfer function of an IIR filter of a feedforward calculation unit with respect to a servo control device configured to control a servo motor configured to drive an axis of a machine tool, a robot, or an industrial machine using feedforward control by a feedforward calculation unit having the IIR filter. The machine learning device represents a zero-point at which the transfer function of the IIR filter is zero and a pole at which the transfer function diverges infinitely in polar coordinates using a radius r and an angle θ, respectively, and searches for and learns, within a predetermined search range, the radius r and the angle θ to thereby perform the optimization of the coefficients of the transfer function of the IIR filter. 1. A machine learning device configured to perform machine learning related to optimization of coefficients of a transfer function of an IIR filter with respect to a servo control device configured to control a servo motor configured to drive an axis of a machine tool , a robot , or an industrial machine using feedforward control by a feedforward calculation unit having the IIR filter , whereinthe machine learning device represents a zero-point at which the transfer function of the IIR filter is zero and a pole at which the transfer function diverges infinitely in polar coordinates using a radius r and an angle θ, respectively, and searches for and learns, within a predetermined search range, the radius r and the angle θ to thereby perform the optimization of the coefficients of the transfer function of the IIR filter.2. The machine learning device according to claim 1 , whereinthe search range of the radius r is defined on the basis of an attenuation factor, and the search range of the angle θ is defined on the basis of a vibration suppression frequency.3. The machine ...

BUILDING MANAGEMENT SYSTEM WITH ONLINE CONFIGURABLE SYSTEM IDENTIFICATION

A building management system includes building equipment operable to affect a variable state or condition of a building and a control system configured to receive a user input indicating a model form. The model form includes a plurality of matrices having a plurality of elements defined in terms of a plurality of parameters. The control system is configured to parse the model form to generate a sequence of machine-executable steps for determining a value of each of the plurality of elements based on a set of potential parameter values, identify a system model by executing the sequence of machine-executable steps to generate a set of parameter values for the plurality of parameters, generate a graphical user interface that illustrates a fit between predictions of the identified system model and behavior of the variable state or condition of the building, and control the building equipment using the identified system model. 1. A building management system comprising:building equipment operable to affect a variable state or condition of a building; and receive a user input indicating a model form, the model form comprising a plurality of matrices having a plurality of elements, one or more of the plurality of elements defined in terms of a plurality of parameters;', 'parse the model form to generate a sequence of machine-executable steps for determining a value of each of the plurality of elements based on a set of potential parameter values;', 'identify a system model by executing the sequence of machine-executable steps to generate a set of parameter values for the plurality of parameters;', 'generate a graphical user interface that illustrates a fit between predictions of the identified system model and behavior of the variable state or condition of the building; and', 'control the building equipment using the identified system model., 'a control system configured to2. The building management system of claim 1 , wherein the control system is configured to identify a ...