Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год

Применить Всего найдено 8. Отображено 8.
23-06-2023 дата публикации

Fuel cell performance degradation prediction method

Номер: CN116306226A
Принадлежит:

The invention discloses a fuel cell performance degradation prediction method, which comprises the following steps of: acquiring voltage degradation data of a fuel cell, smoothing original data by adopting an SG filter, selecting auxiliary variables of the data by applying grey relational analysis, and establishing a performance degradation prediction model based on Bagging ensemble learning and a time convolutional network; performing initialization operation on the population of the manta ray foraging optimization algorithm by adopting half uniform initialization, and introducing an adaptive weight and a fitness-distance balance strategy in chain foraging position updating to obtain IMRFO; bagging ensemble learning is used to carry out fusion prediction on a plurality of weak learners, the prediction result of the first layer is used to train a TCN model, IMRFO is used to carry out parameter optimization on the TCN to obtain optimal parameters, and the optimal parameters and test data ...

Подробнее
03-09-2014 дата публикации

Hydraulic puller

Номер: CN104015156A
Принадлежит:

The invention provides a hydraulic puller, and relates to a hydraulic tool which can be operated in narrow space and used for disassembling a coupling which is a transmission component between a motor and a pump. The hydraulic puller mainly solves the problems that an existing method for disassembling the transmission component, namely the coupling, between the motor and the pump comprises the steps of heating the coupling through flames and making the coupling retreat through knocking of a copper rod, the coupling and a bearing expand with heat at the same time and fail to retreat smoothly, the coupling and the bearing are prone to damage in the knocking process, much labor and time are consumed, and potential safety hazards are caused to operation of the pump. The hydraulic puller comprises a puller back plate and a hydraulic cylinder connected to the puller back plate. The hydraulic puller is characterized in that an oil injection hole communicated with the hydraulic cylinder is formed ...

Подробнее
23-05-2023 дата публикации

Auxiliary test device, collision test system and collision test method

Номер: CN116147872A
Принадлежит:

The invention discloses an auxiliary test device, a collision test system and a collision test method. The auxiliary test device comprises a test box body, a test mainboard arranged in the test box body and a test configuration area arranged on the test box body, the test configuration area is provided with a wire harness plug connector electrically connected with the test mainboard and a plug connector used for being connected with an air bag restraint system controller. The test mainboard is connected with the test upper computer and the safety air bag controller, and is used for simulating a whole vehicle test environment according to the plugging state of the wire harness plug connector, forming a first collision acceleration in a whole vehicle collision test process, sending the first collision acceleration and an effective ADAS signal output by the test upper computer to the safety air bag controller, and sending the effective ADAS signal to the test upper computer; therefore, the ...

Подробнее
23-06-2023 дата публикации

Nitrogen oxide predicted emission detection method and system of gas turbine

Номер: CN116306234A
Принадлежит:

The invention discloses a method and a system for detecting nitrogen oxide predicted emission of a gas turbine. The method comprises the following steps: acquiring variable data on a gas turbine sensor; and selecting parameters with high importance by adopting a random forest. LSH (Local Sensitive Hash) is used for optimizing an informer model, and the model is used for predicting nitrogen oxide emission of a gas turbine of a power plant; inputting the selected parameters and variables into an improved informer model, carrying out parameter adjustment on the informer model, and finding out a hyper-parameter which has the greatest influence on the informer model; improving a chaos game optimization algorithm, and adding an elite reverse learning mechanism and golden sine; and further optimizing hyper-parameters of the model by using an improved algorithm. The method is used for predicting nitric oxide of the gas turbine of the power plant, the nitric oxide prediction precision is improved ...

Подробнее
11-04-2023 дата публикации

Sewage treatment process soft measurement modeling method based on integrated deep learning

Номер: CN115952685A
Принадлежит:

The invention discloses a sewage treatment process soft measurement modeling method based on integrated deep learning. Firstly, sewage data is acquired as an auxiliary variable; performing KPCA feature selection on the collected variables to serve as the input of the model; a sewage soft measurement integrated model is established, the integrated model has two layers, the first layer comprises three base learners of BiLSTM, LSSVM and XGBoost, a five-fold cross validation method is adopted for training, and ELM is adopted as a meta learner in the second layer; and finally, performing error correction on the initial prediction result by adopting an extreme learning machine. In order to improve the performance of the model, an RSA algorithm is proposed to optimize model parameters; and according to the problems of the RSA algorithm in the aspects of convergence precision, easy falling into local optimum and the like, Latin hypercube, a nonlinear factor, golden sine and a tumbling strategy ...

Подробнее
15-07-2015 дата публикации

Steering wheel and driver safety airbag module matching structure

Номер: CN104773129A
Принадлежит:

The invention discloses a steering wheel and driver safety airbag module matching structure, comprising an airbag module housing, a steering wheel skeleton and a spring wire; the spring wire is movably arranged on the housing; a stop hook is arranged at a position, corresponding to the spring wire, on the steering wheel skeleton; the stop hook clamps the spring wire. The steering wheel and driver safety airbag module matching structure disclosed by the invention is located by matching between the stop hook and the spring wire, so that the matching between the steering wheel and the driver safety airbag module as well as fixing reliability requirements for airbag blasting can be effectively realized; with a plastic coated piece on the spring wire, the abnormal sound problem when a horn is pressed can be effectively solved.

Подробнее
30-06-2023 дата публикации

Optimization control method for sewage treatment process

Номер: CN116360366A
Принадлежит:

The invention discloses an optimization control method for a sewage treatment process. The optimization control method comprises the steps of data acquisition, data preprocessing, prediction model establishment and optimization control design. The data acquisition unit is used for acquiring data of various chemical components in the sewage treatment process; the data preprocessing performs feature selection on the obtained data, so that the calculation complexity of the data is reduced; the method comprises the following steps: establishing a prediction model, firstly training the model, establishing a sewage treatment process prediction model based on an integrated depth random vector function link network to obtain optimal parameters, then optimizing the prediction model by using an improved arithmetic optimization algorithm to improve the prediction capability of the model, and finally predicting acquired sewage data; according to the optimization control design, a prediction result ...

Подробнее
11-04-2023 дата публикации

Soft measurement prediction method for nitrite nitrogen concentration

Номер: CN115952728A
Принадлежит:

The invention discloses a soft measurement and prediction method for nitrite nitrogen concentration, which comprises the following steps of: acquiring culture water plant data, selecting auxiliary variables from the data by using a principal component analysis method, obtaining four auxiliary variables, namely temperature, pH, dissolved oxygen and oxidation-reduction potential, which influence the nitrite nitrogen concentration, measuring the nitrite nitrogen concentration in a water body, preprocessing the data, and predicting the nitrite nitrogen concentration. Establishing an ELM (Extreme Learning Model)-based nitrite nitrogen concentration soft measurement prediction model; latin hypercube sampling is adopted to carry out initialization operation on an SSA population, and Logistic mapping and a nonlinear dynamic weight strategy are introduced into position updating of a dogvessel leader; in the position updating of the follower, a gravitational search strategy is introduced to obtain ...

Подробнее