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.
16-05-2023 дата публикации

High-speed railway track multi-target fine adjustment method under data physical fusion

Номер: CN116127631A
Автор: HE QING, SUN HUAKUN, WU SHIFENG, LI CHENZHONG, DING WENHAO, WANG PING, ZUO XUAN, ZHAO LINYUAN, CHEN QIANG, LI CHANG, WAN SHUAI, XU CONGYANG
Принадлежит:

The invention relates to the technical field of track fine adjustment, in particular to a high-speed railway track multi-target fine adjustment method under data physical fusion, which comprises the following steps of: 1) determining a target function of a multi-target optimization model; 2) establishing a model constraint adjacent pillow physical coupling relationship; 3) adding conventional constraint conditions; 4) determining an optimal solution of the track state; and 5) an iterative optimization process. According to the method, the problems that time and labor are consumed in the formulation process of a track fine adjustment scheme and a difference exists between a theoretical adjustment scheme and an actual adjustment effect can be solved, optimization of the track irregularity state and optimization of the adjustment amount under the complex constraint condition are effectively guaranteed, and the maintenance workload of public work personnel is greatly reduced.

Подробнее
Номер записи: 1
09-05-2023 дата публикации

Enterprise credit condition evaluation method

Номер: CN116091195A
Автор: ZENG TAO, ZHU XIQING, ZHAO JIN, LI QINGTIAN, ZHANG QIANG, ZHANG KUAN, FENG FENG, SUN HUAKUN, CHEN JING
Принадлежит:

The invention provides an enterprise credit condition evaluation method, which comprises the following steps of: calling industry and commerce data, tax data, reward and punishment data, financial data, electric power data, communication data, industry data, public credit data, intellectual property data, science and technology research and development capability data, green emission reduction data and social contribution data on an enterprise on a platform; establishing a risk database of the enterprise; the relevance between the data and the enterprise performance capability is calculated, related numerical values are scored, legal and compliant operation of the enterprise is recorded as a positive number if the data is good, illegal and compliant operation of the enterprise is recorded as a negative number if the data is poor, and the better the data is, the larger the recorded numerical value is; setting the proportion of each influence primer, wherein the industrial and commercial ...

Подробнее
Номер записи: 2
23-06-2023 дата публикации

Mileage alignment method and system for high-frequency sampling data of high-speed railway dynamic inspection vehicle

Номер: CN116304954A
Автор: HE QING, YANG FEI, LI-WANG YIJIA, LI CHENZHONG, SUN HUAKUN, MA YUSONG, WANG PING, GAO MANGMANG, QU JIANJUN, SUN XIANFU, DENG YAJIE, XU CONGYANG, LIU YUHENG
Принадлежит:

The invention provides a mileage alignment method and system for high-frequency sampling data of a high-speed railway dynamic inspection vehicle, and belongs to the technical field of mileage alignment of rail traffic data, the method can be realized through the system, and the method comprises the following steps: S1, extracting speed data in axle box acceleration data and speed data in wheel-rail force data; s2, carrying out long unit mileage error correction on the axle box acceleration data and the wheel-rail force data; and S3, carrying out short unit mileage error correction on the axle box acceleration data and the wheel-rail force data. According to the method, the analysis accuracy of the high-frequency sampling data of the dynamic inspection vehicle can be greatly improved.

Подробнее
Номер записи: 3
09-05-2023 дата публикации

Method for controlling local financial risk through enterprise credit

Номер: CN116091196A
Автор: ZHU XIQING, ZENG TAO, ZHAO JIN, ZHANG QIANG, LI QINGTIAN, FENG FENG, ZHANG KUAN, SUN HUAKUN, CHEN JING
Принадлежит:

The invention provides a method for regulating and managing enterprise credit and controlling local risks by analyzing enterprise credit conditions by means of enterprise-related data on the basis of actual business requirements developed by units such as a Hebei province financial service platform and a financial institution. The most accurate enterprise-related data (industry and commerce, judicial, taxation, reward and punishment, finance, electric power and the like) is directly obtained through each provincial office, after data collection is completed, enterprise risk label calculation, risk level and risk influence evaluation and risk processing scheme definition are realized by utilizing a big data analysis technology and a self-research enterprise credit evaluation algorithm and combining local financial risk classification, and the enterprise risk management and risk management are realized. A credit five-color map (two-dimensional codes) is constructed, colors are marked according ...

Подробнее
Номер записи: 4
04-04-2023 дата публикации

Bearing vibration detection and recognition method based on octave and voting mechanism

Номер: CN115901258A
Автор: ZHAO JINGPING, XU HAIRONG, LI PEIHAI, HE QING, SUN HUAKUN
Принадлежит:

The invention relates to the technical field of railway vehicle detection, and discloses a bearing vibration detection and identification method based on an octave and a voting mechanism, and the method comprises the steps: completing the bearing detection of a passing vehicle through a bearing running-in test bench disposed at a railway site, and forming actual detection data; the bearing running-in test bench comprises a contact part used for being in direct contact with an outer ring of a tested bearing, and the contact part is provided with an acceleration sensor and a microphone. The acceleration sensor detects the vibration of the bearing to form vibration acceleration data. Bearing vibration is detected through a microphone to form sound pressure level data; the vibration acceleration data and the sound pressure level data together form vibration transmission data. The method can more accurately complete the detection and recognition of the vibration of the bearing, and can be applied ...

Подробнее
Номер записи: 5
25-08-2023 дата публикации

Truck bearing abnormal feature extraction and classification method based on similarity

Номер: CN116644304A
Автор: LI PEIHAI, HE QING, SUN HUAKUN, DUAN YIXIAN, LI CHENZHONG, LIU TAO, LI-WANG YIJIA, CHEN YUBING, XU CONGYANG
Принадлежит:

The invention relates to the technical field of anomaly detection, and discloses a truck bearing anomaly feature extraction and classification method based on similarity, and the extraction method comprises the following steps: 1, collecting basic data; the basic data comprises a time domain acceleration signal of a truck bearing; 2, preprocessing the basic data, and dividing the basic data into a training set and a test set; converting time domain data in the training set and the test set into frequency domain data; 3, establishing a twin network feature extraction model; a feature calculation network and a twin network which is twin with the feature calculation network are arranged in the established twin network feature extraction model; the feature calculation network and the twin network have the same structure and share parameters; and 4, carrying out feature extraction by adopting a twin network feature extraction model. According to the invention, the method can intelligently and ...

Подробнее
Номер записи: 6
23-06-2023 дата публикации

Track irregularity dynamic and static detection data inversion method and system and storage medium

Номер: CN116307302A
Автор: HE QING, MA YUSONG, LI CHENZHONG, SUN HUAKUN, LI-WANG YIJIA, WANG PING, LIU SANJUN, WANG DECHANG, GUO YANHUA, FAN QIANG, LI ZHIQIANG, ZHAO JIANJUN, CHANG ZHITING, YU WEIDONG, SUN GUIBO
Принадлежит:

The invention provides a track irregularity dynamic and static detection data inversion method and system and a storage medium, and belongs to the technical field of data inversion, the system is used for executing the method, and the method comprises the following steps: S1, obtaining original data; s2, preprocessing the original data to obtain preprocessed data; s3, extracting track irregularity peak data based on the preprocessed data, and performing data transformation operation to obtain test set data; s4, improving the bidirectional long-short-term memory network model; s5, optimizing and improving the bidirectional long-short-term memory network model; s6, performing model training, and solving the optimizer to obtain an optimization model; and S7, inputting test set data into the optimization model to obtain a test result, and completing data inversion. According to the method, the geometric state of the track can be predicted and evaluated more comprehensively.

Подробнее
Номер записи: 7
25-08-2023 дата публикации

Double-model bearing anomaly detection algorithm based on sample screening and feature extraction

Номер: CN116644278A
Автор: LI PEIHAI, HE QING, SUN HUAKUN, LIU TAO, LI CHENZHONG, DUAN YIXIAN, CHEN YUBING, LI-WANG YIJIA, XU CONGYANG
Принадлежит:

The invention relates to the technical field of anomaly detection, and discloses a dual-model bearing anomaly detection algorithm based on sample screening and feature extraction, comprising the following steps: step 1, collecting initial data and preprocessing; the initial data is a transmission vibration acceleration signal of the wheel set; 2, dividing the preprocessed initial data into a training set and a test set according to a proportion; 3, establishing a sample screening model; positive samples and negative samples which can be used for feature extraction are screened out by adopting a sample screening model; 4, establishing a feature extraction model; the feature extraction model comprises a triple feature extraction network; and 5, establishing a feature classification model, carrying out feature classification on the extracted positive samples and negative samples, and carrying out a recognition task of unfamiliar samples by training a classification boundary. According to the ...

Подробнее
Номер записи: 8