Equipment fault diagnosis method with adaptive learning rate based on deep learning

Abstract

The invention relates to an equipment fault diagnosis method with an adaptive learning rate based on deep learning. According to the method, a trained fault diagnosis model based on deep learning is used for processing to-be-diagnosed data collected in real time, wherein the fault diagnosis model adopts an adaptive learning rate to carry out iterative computation. The adaptive learning rate is specifically as follows: on the basis of the last round of learning rate, the current gradient value is used for adaptively adjusting the current round of learning rate. Compared with the prior art, themethod has the advantages of short model training time, high classification accuracy and the like.

Description

technical field [0001] The present invention relates to a method for diagnosing equipment faults, in particular to a method for diagnosing equipment faults with an adaptive learning rate based on deep learning. Background technique [0002] The performance of the equipment will gradually decline with the increase of service time, and the effective diagnosis of the fault type of the equipment is of great significance for the timely maintenance of the equipment. Fault diagnosis refers to excavating the internal evolution law of equipment fault signals to realize the classification of equipment fault types, and to perform fault diagnosis to facilitate equipment maintenance and management. [0003] Traditional fault diagnosis methods include methods based on analytical models, methods based on signal processing, methods based on knowledge, and methods based on data. However, the first three methods are often limited by knowledge such as professional technology and expert experi...

AI Technical Summary

Problems solved by technology

[0006] Some of the above achievements provide some feasible methods, but these methods do not distinguish between the weight and bias parameters in the deep learning model, but use an adaptive learning rate strategy uniformly, which will have certain limitations

A globally unified learning rate strategy is not necessarily suitable for the adjustment rate of all parameters, but will reduce the iteration rate of the model and increase the training time of the model

Images