Rolling bearing fault diagnosis method for improving model migration strategy

Abstract

The invention discloses a rolling bearing fault diagnosis method for improving a model migration strategy, and belongs to the technical field of rolling bearing fault diagnosis. The method is providedfor solving the problem of large distribution difference of data in the same state in a source domain and a target domain, and comprises: obtaining time-frequency spectrums of vibration signals of different types of bearings through wavelet transform, and constructing an image data set; selecting data of a certain model as a source domain, and selecting data of other models as a target domain; training a ResNet-34 deep convolutional network by using the source domain data to obtain a source domain data classification model; adaptively determining a migration knowledge level and knowledge content by using implicit gradient meta-learning to realize improvement of a model migration strategy and avoid a phenomenon that a gradient in a heterogeneous system structure is not easy to converge; introducing the migrated knowledge into a target domain ResNet-152 convolutional neural network data training process, and realizing model migration through parameter transmission; and optimizing network parameters by adopting a stochastic gradient descent algorithm when the source domain network and the target domain network are trained, and establishing fault diagnosis models of different types ofrolling bearings.

Description

technical field [0001] The invention relates to a rolling bearing fault diagnosis method with an improved model migration strategy, and belongs to the technical field of rolling bearing fault diagnosis. Background technique [0002] As a key component of rotating machinery, rolling bearings are widely used in industrial production, and effective fault diagnosis can prevent major accidents [1] . There are various types of rolling bearings, resulting in the lack of or inability to obtain training data of a certain type with labels in actual work [2] . It is of great practical significance to identify the state of vibration signals with unknown state information based on the vibration signals of rolling bearings with known state information. [3] . [0003] The fault diagnosis of different positions and different damage degrees of rolling bearings is essentially the identification of the operating status of rolling bearings [4] . The traditional state recognition method ne...

AI Technical Summary

Problems solved by technology

[0009] The present invention aims at the problems that it is difficult to obtain the vibration data of a certain type of rolling bearing in practice, the data distribution of the same state in the source domain and the target domain is greatly different, and when the vibration data of different types of rolling bearings are selected for different domains, different fault locations and different The accuracy of damage degree identification is not high, and then a rolling bearing fault diagnosis method with improved model migration strategy is proposed

Images