Rolling bearing fault diagnosis method based on full convolution auto-encoder and optimized support vector machine

Abstract

The invention discloses a rolling bearing fault diagnosis method based on a full convolution auto-encoder and an optimized support vector machine, and belongs to the field of bearing fault diagnosis. Firstly, due to the fact that a traditional fault feature is difficult to extract and the generalization of the feature is weak, the invention provides a fault diagnosis method based on a full-convolution auto-encoder, and the full-convolution auto-encoder has the advantages of a convolutional neural network and an auto-encoder at the same time; a stacked full-convolution auto-encoder is adopted to automatically extract depth fault features from the bearing vibration signal frequency spectrum; then, the Fisher criterion is used for grading and sorting the extracted depth fault features, the criterion is based on the intra-class distance and the inter-class distance, and the fault features with high discrimination can be screened out; and finally, optimizing hyper-parameters of the SVM by adopting an improved doliolaria algorithm, and inputting the screened features into the optimized SVM to complete fault identification of the rolling bearing.

Description

technical field [0001] The invention belongs to the field of bearing fault diagnosis and relates to a rolling bearing fault diagnosis method based on a full convolution autoencoder and an optimized support vector machine. Background technique [0002] With the development of industry, mechanical equipment is increasingly networked and automated, and the connection between equipment is getting closer. These systematic equipment are widely used in important engineering fields such as energy, petrochemical, and metallurgy. Once a certain part of the equipment fails, it will trigger a series of chain reactions. Equipment failure will not only cause huge economic losses, but also trigger a series of catastrophic consequences. Rolling bearings are called "industrial joints" and are one of the basic components of large mechanical equipment. Rolling bearings have been in working condition for a long time, the working conditions are complex and changeable, and the working environme...

AI Technical Summary

Problems solved by technology

Aiming at the problems of incomplete signal effective feature extraction, low fault diagnosis accuracy and low efficiency in existing coal mine rotating machinery rolling bearing fault diagnosis methods, the literature [Ju Chen, Zhang Chao, Fan Hongwei, etc. Rolling Bearing Based on Wavelet Packet Decomposition and PSO-BPNN Fault Diagnosis [J]. Industrial and Mine Automation, 2020,46(08):70-74] proposed a rolling bearing fault diagnosis method based on wavelet packet decomposition and particle swarm optimization BP neural network

Images