213 / 2024-09-02 10:14:31

Fault diagnosis of rolling bearings based on wavelet and BP neural networks

Rolling bearing, Fault diagnosis, Wavelet analysis, BP neural network.

A rolling bearing fault diagnosis method based on wavelet transform and BP neural network is proposed to address the problem of excessive interference noise in the vibration signal of belt conveyor rolling bearings, which affects fault diagnosis. Firstly, the signal is decomposed using wavelet transform, and the fault feature vector is extracted using wavelet band energy method. Then, a Bp neural network model is constructed using the fault feature vector and the target output vector. Finally, use the test feature vector samples as input to determine the type of rolling bearing operating conditions. Through experimental analysis of rolling bearing faults, the results show that this method can effectively recognize the normal state, outer ring faults, inner ring faults, and rolling element faults of rolling bearings. This indicates that the method can correctly diagnose faults in rolling bearings.