Rolling bearing fault diagnosis method based on vibration signal

Abstract

The invention relates to a rolling bearing fault diagnosis method based on a vibration signal. A CEEMDAN algorithm is adopted to decompose the vibration signal, de-trending fluctuation analysis is carried out on an obtained intrinsic mode function, a scale function value of each IMF component is calculated, and a noise dominant IMF component is selected to carry out de-noising processing; the noise can be better removed, and the distortion degree of the signal is reduced; calculating correlation coefficients and kurtosis values of all orders of IMF components, selecting IMF components with relatively large correlation coefficients and kurtosis values to perform signal reconstruction, performing Hilbert envelope spectrum analysis on reconstructed signals, extracting fault feature frequency, introducing a grey wolf algorithm to optimize initial parameters of multi-scale permutation entropy, performing MPE value calculation on the reconstructed signals, selecting a proper MPE value to construct a rolling bearing fault feature set, and inputting a fault feature vector into the trained support vector machine to carry out rolling bearing fault recognition, so that the entropy discrimination degree is high, the constructed fault feature vector is better, and the recognition rate is higher.

Description

technical field [0001] The invention relates to a rolling bearing fault diagnosis method, in particular to a rolling bearing fault diagnosis method based on vibration signals. Background technique [0002] Rolling bearings are the core components of rotating machinery, and they are also extremely vulnerable to damage. If a rolling bearing fails, it will cause the production line to stop working at least, and cause casualties at worst. Therefore, it is necessary to carry out fault diagnosis on the bearing, determine its fault location, and repair or replace the faulty parts in time. [0003] For different components of rolling bearings to fail, their operating cycles and structural dimensions are different, which leads to different frequencies of bearing failures. [0004] At present, there are two main denoising methods for bearing vibration signals: one is based on wavelet threshold denoising method, and the other is based on empirical mode decomposition (EMD) denoising me...

AI Technical Summary

Problems solved by technology

At present, the commonly used fault type methods are mainly artificial neural network and SVM. Among them, fault type identification based on support vector machine, support vector machine can better solve the defect of artificial neural network with poor learning results when the number of samples is small, but support vector machine The parameters need to be optimized, otherwise the recognition accuracy is not high

Simple MPE-SVM recognition, there is MPE entropy aliasing phenomenon

Images