Fault diagnosis method based on cloud edge collaboration and adaptive knowledge transfer

The invention provides a fault diagnosis method based on cloud edge collaboration and adaptive knowledge transfer, and relates to the technical field of fault diagnosis, comprising the following steps: acquiring operation state data of a gearbox, and performing oversampling processing on the operation state data to obtain a training data set; constructing a first model and a second model, and performing iterative training on the first model by using the training data set to obtain a first prediction result of the first model on the training data set; performing iterative training on a second model by using the training data set in combination with the first prediction result and a knowledge transmission method to obtain an optimized second model; and deploying the optimized second model in the edge computing device, collecting real-time data from the gearbox, and importing the optimized second model for detection to obtain a fault diagnosis result. According to the method, computing resources of the cloud end