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.
02-05-2023 дата публикации

Remote sensing image cloud and cloud shadow fine segmentation detection method based on deep learning

Номер: CN116052016A
Принадлежит:

The invention discloses a remote sensing image cloud and cloud shadow fine segmentation detection method based on deep learning, and belongs to the field of image processing. The detection method comprises the following steps: acquiring and processing a training data set, and dividing the data set into a training set and a verification set; constructing a segmentation network for deep learning semantics; training a network model in the segmentation network by using the data set; predicting by using the trained network model and generating mask images of the cloud and the cloud shadow; a segmentation network ResNet-18 network is used as a trunk to extract feature information of different levels, attention of a model to channel information and space information is enhanced through a multi-scale global attention module to improve the segmentation accuracy, and a strip-shaped pyramid channel attention module is used for learning the space information in a multi-scale mode to better detect fine ...

Подробнее
13-06-2023 дата публикации

Peculiar smell gas purification pretreatment process in wet garbage disposal process

Номер: CN116251468A
Принадлежит:

The invention discloses a peculiar smell gas purification pretreatment process in a wet garbage disposal process. A catalytic reaction bed is composed of an iron-based material, copper oxide, manganese dioxide, aluminum oxide and a carbon-based material, the catalytic reaction bed forms a primary battery in the leaching process of weak acid leacheate, and a nascent electrode product is extremely high in activity and can be subjected to an oxidation-reduction reaction with peculiar smell gas, so that the peculiar smell gas can be generated; the structure and the form of a non-biodegradable part in the peculiar smell gas are changed and are converted into an easily biodegradable substance, so that the treatment efficiency of a subsequent biological purification unit is favorably improved. Besides, ferrous ions generated through electrolysis generate ferric ions under the action of oxygen, ferric hydroxide and ferrous hydroxide polymers are formed through hydrolysis and polymerization, the ...

Подробнее
29-08-2023 дата публикации

Semi-dry deacidification equipment

Номер: CN116651189A
Принадлежит:

The semi-dry method deacidification equipment comprises an air supply pipeline and a wet powder conveying pipeline which are sequentially communicated in the material conveying direction, the air supply pipeline is communicated with a feeding mechanism for quantitatively supplying deacidification dry powder to the air supply pipeline, a contracted pipe is communicated between an air outlet of the air supply pipeline and the wet powder conveying pipeline, and the circulation cross section of the contracted pipe is gradually reduced in the air supply direction. The wet powder conveying pipeline comprises a first throat pipe section and a first expansion pipe section which are sequentially communicated in the air supply direction, the first throat pipe section is in butt joint with an outlet of the contracted pipe, the circulation section of the first throat pipe section is matched with the structure of the outlet of the contracted pipe and communicated with a water supply mechanism for quantitatively ...

Подробнее
23-06-2023 дата публикации

Cloud snow identification method and device based on multi-level attention interaction and storage medium

Номер: CN116310868A
Автор: XIA MIN, DING LI
Принадлежит:

The invention discloses a cloud snow identification method and device based on multi-level attention interaction and a storage medium, and relates to the technical field of image processing, and the method comprises the steps: obtaining a to-be-identified image; inputting the image to be recognized into a pre-trained multi-level attention interaction network; wherein the multi-level attention interaction network comprises a down-sampling feature extraction module, a detail feature extraction module, a deep multi-head attention information enhancement module and a feature interaction fusion up-sampling module; and according to the output of the multi-level attention interaction network, obtaining mask images of the cloud and the snow, and completing identification of the cloud and the snow. According to the method, cloud and snow identification under interference of various ground backgrounds can be realized, the detection capability on thin cloud and snowfield edges is enhanced, the influence ...

Подробнее
25-07-2023 дата публикации

Smart power grid anomaly detection and classification method and device, and readable storage medium

Номер: CN116488325A
Принадлежит:

The invention belongs to the technical field of power grid anomaly detection, and particularly relates to a smart power grid anomaly detection and classification method and device and a readable storage medium. The method comprises the steps that 1, a proper training data set is obtained, 2, an anomaly detection and classification system (ADCS) is constructed, and the anomaly detection and classification system comprises a self-encoding and generative adversarial network architecture and is divided into system structures under the two conditions of anomaly detection and anomaly classification; step 3, training an anomaly detection and classification system network, preprocessing training data, and formatting the data by using a sliding window; 4, inputting a test data set of the smart power grid, carrying out encoding and decoding operation on data formed by normal and abnormal time sequence electrical measurement through the trained anomaly detection and classification system network, ...

Подробнее
29-08-2023 дата публикации

Household garbage incineration fly ash high-temperature melting and curing method for reducing refractory material erosion

Номер: CN116655243A
Автор: CHEN CHAO, WANG QINQIN, XIA MIN
Принадлежит:

The invention discloses a household garbage incineration fly ash high-temperature melting and curing method for reducing erosion of a refractory material, which is characterized in that the addition amount of quartz sand in fly ash is reduced, and the proportion of Al2O3 and CaO is regulated and controlled, so that the fly ash is cured, the leaching toxicity of heavy metal reaches the standard, and meanwhile, the erosion of the fly ash to the refractory material is reduced. The raw material components comprise, by mass, 40-50% of fly ash, 20-40% of Al2O3, 10-15% of limestone, and 0-5% of quartz sand. The melting temperature is 1400 to 1600 DEG C. Fly ash fusion and solidification are achieved by regulating and controlling the content of CaO and Al2O3 and reducing the adding amount of quartz sand, heavy metal leaching reaches the standard, meanwhile, erosion of the fly ash to a refractory material is reduced, and the service life of a lining is prolonged.

Подробнее
14-07-2023 дата публикации

Land coverage detection method, system and equipment based on multi-scale position attention aggregation

Номер: CN116434077A
Автор: XIA MIN, DAI XIN
Принадлежит:

The invention discloses a land coverage detection method, system and equipment based on multi-scale position attention aggregation. The method comprises the steps of obtaining training data, and then constructing a multi-scale position attention aggregation network; training a multi-scale position attention aggregation network, performing data enhancement processing on an image in the training data, then converting the image and a corresponding label into a tensor, and inputting the tensor into the multi-scale position attention aggregation network for training; and finally, performing prediction by using the trained multi-scale position attention aggregation network, performing encoding and decoding operation on the trained weight extraction features, and outputting to obtain mask images of the building and the water area. According to the method, the misclassification phenomenon caused by interference of a complex background can be effectively reduced, the edge detection capability of ...

Подробнее
14-07-2023 дата публикации

Remote sensing image change detection method based on local-global Transform network

Номер: CN116434069A
Автор: XIA MIN, SONG LEI
Принадлежит:

The invention discloses a remote sensing image change detection method based on a local-global Transform network. The method comprises the following steps: preprocessing multiple groups of image sample data to obtain multiple groups of image data; each group of standardized image data is input into a local-global Transform network, and each group of standardized image data is input into the local-global Transform network; performing differential operation on the output of the previous time-phase remote sensing image and the output of the later time-phase remote sensing image in each stage, and then inputting into a high-frequency enhancement unit to obtain the high-frequency characteristics of the edge of the change area in each stage; inputting the high-frequency features of the second stage, the third stage and the fourth stage into a multi-scale fusion attention unit to obtain fine-grained fusion features of each stage; inputting the high-frequency features of the edge of the change ...

Подробнее