30-05-2023 дата публикации
Номер: CN116192620A
Принадлежит:
A fault detection model training method, a fault detection method, a fault detection device and a fault detection system are characterized in that an end-edge-cloud three-layer architecture is constructed, a cloud end is responsible for training and subsequent updating of an initial fault detection model, an edge server is responsible for training of a local model, and a terminal uses the fault detection model to perform fault detection; the fault detection precision, the detection efficiency and the data privacy of the terminal are considered in the whole process; data transmission of the terminal, the edge server and the cloud is reduced through modes of data compression of the terminal, transmission of fault detection model parameters and the like, network bandwidth use is reduced, and model updating efficiency is improved; three different model updating strategies are provided, the model updating speed and the model precision can be balanced, and different application requirements are ...
Подробнее