Multi-view intelligent fault diagnosis method and system for explosion-proof motor bearing

Abstract

The invention relates to an explosion-proof motor bearing multi-view intelligent fault diagnosis method and system. The method comprises the following steps: establishing a feature enhancement network; fusing the feature enhancement network and the bidirectional long short-term memory network to form a multi-view deep transfer learning network; using domain adaptive learning to measure the distribution difference between domain invariant features extracted from a source domain data set and a target domain data set through the multi-view deep transfer learning network, and using the domain invariant features extracted from a labeled source domain data set to train a domain sharing category classifier; distribution difference and classification loss generated in the process jointly form an objective function needing to be optimized for network updating, the objective function is optimized through back propagation and gradient descent algorithms, network parameters are updated, and a trained network is obtained; and inputting a to-be-tested vibration signal into the trained network to obtain a fault category of a label-free sample in the target domain data set. The method has good generalization performance.

Description

technical field [0001] The invention relates to the technical field of intelligent operation and maintenance of explosion-proof motors, in particular to a multi-view intelligent fault diagnosis method and system for explosion-proof motor bearings. Background technique [0002] The bearing is one of the core components of the explosion-proof motor. It supports the motor shaft and bears the load. It plays an important role in the power transmission and power consumption reduction in the transmission system of the explosion-proof device. Therefore, its service performance has an important impact on the normal operation of the explosion-proof motor. . Since the explosion-proof motor is mainly used in the special working environment of flammable and explosive places, a weak explosion-proof motor bearing failure may cause serious consequences such as shutdown of the device or even death of the machine. Therefore, it is of great significance to carry out the research on the intell...

AI Technical Summary

Problems solved by technology

[0006] For this reason, the technical problem to be solved by the present invention is to overcome the problems in the prior art that the learned feature representation ability is insufficient and the generalization performance is poor, thus affecting the diagnostic accuracy, thereby providing a learned feature representation ability with strong generalization performance. Multi-view intelligent fault diagnosis method and system for explosion-proof motor bearings with good performance and improved diagnostic accuracy

Images