Bearing fault feature enhancement method and system

Abstract

The invention discloses a bearing fault feature enhancement method and system. The method comprises the following steps: acquiring multiple groups of bearing data based on a compressed sensing theory;obtaining an optimized measurement matrix by adopting a gradient projection method according to the bearing data; wherein the optimized measurement matrix is composed of an optimized sparse base measurement matrix and a base measurement matrix; reconstructing the bearing data by adopting an orthogonal matching pursuit algorithm according to the optimized measurement matrix to obtain bearing reconstruction data; decomposing the bearing reconstruction data by adopting an empirical wavelet transform method to obtain a plurality of bearing reconstruction component data; denoising the reconstructed component data of each bearing by adopting a wavelet threshold function method to obtain processed reconstructed component data of each bearing; reconstructing the processed bearing reconstruction component data by adopting an empirical wavelet transform method to obtain a reconstruction signal; wherein the reconstruction signal is bearing data after bearing fault feature enhancement. Accordingto the invention, the reconstruction accuracy can be improved.

Description

technical field [0001] The invention relates to the field of vibration signal analysis, in particular to a bearing fault feature enhancement method and system. Background technique [0002] For rolling bearing faults, how to extract information that can represent the fault characteristics from the collected signals is the basis for effective diagnosis. One or several shock signals will be generated every time the faulty bearing rotates. Analyzing these shock signals is an effective way to obtain fault characteristics. Since the bearing signal is relatively weak, it is easily overwhelmed by strong background noise. How to effectively filter out noise and interference information, amplify the impact signal, and effectively extract important information from the bearing signal has become a prerequisite for fault diagnosis. [0003] In the bearing fault feature enhancement method, the compressive sensing theory is usually adopted. The compressive sensing theory reduces the diff...

AI Technical Summary

Problems solved by technology

However, the hardware implementation cost of the Gaussian random measurement matrix is ​​high, and the deterministic matrix generally has the problem of poor compression and reconstruction effect, which will lead to a large error between the enhanced result of the bearing fault feature and the original signal, and the accuracy of the reconstruction Low, affecting the accuracy of subsequent fault feature extraction and fault diagnosis

Images