Rolling bearing fault diagnosis method and system

Abstract

The invention discloses a rolling bearing fault diagnosis method and system, and belongs to the technical field of rolling bearing fault analysis, and the method comprises the following steps: collecting different state signals of a rolling bearing; carrying out fault feature extraction by using a time shift weighted multi-scale fuzzy entropy algorithm TSWMFE, and comprehensively constructing a high-dimensional fault feature set of the rolling bearing from multiple scales; carrying out dimension reduction screening on the high-dimensional fault feature set of the rolling bearing by utilizing an improved generalized regularization coplanar discriminant analysis algorithm IGRCDA to obtain a low-dimensional fault feature set which is convenient to recognize and sensitive; and training the support vector machine COA-SVM optimized by the suburb wolf optimization algorithm by using the low-dimensional fault feature set, and performing fault diagnosis by using the trained suburb wolf optimization algorithm optimized support vector machine COA-SVM. The rolling bearing fault feature extraction method solves the problem that the rolling bearing fault feature extraction is difficult, can effectively and accurately diagnose each fault type of the rolling bearing, and is worthy of being popularized and used.

Description

technical field [0001] The invention relates to the technical field of rolling bearing fault analysis, in particular to a rolling bearing fault diagnosis method and system. Background technique [0002] As an important part of rotating machinery, rolling bearings are responsible for the connection between the rotor and the stator. Their operating status has an important impact on whether the rotating machinery can work stably for a long period of time. Faults may even cause serious safety accidents, so fault diagnosis has important theoretical and practical significance. [0003] The signals of rolling bearings are usually characterized by non-stationary and nonlinear characteristics. Therefore, many nonlinear time-series complexity methods for measuring mechanical dynamic systems have been proposed and applied in the field of fault diagnosis. Among them, time-shifted multi-scale fuzzy entropy (TSMFE) combines the idea of ​​time-shifting, and solves the problem that the coa...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is: how to solve the problem of difficult feature extraction of rolling bearing faults in the prior art and the problem of removing redundant information through secondary feature extraction, and provides a rolling bearing fault diagnosis method that can effectively and accurately diagnose rolling bearing faults. various failure types

Images