Fault Diagnosis of Rolling Bearing Based on Wavelet Packet and RBF Neural Network

Abstract

Listen

Translate article

Rolling bearing is a key part of the robot, but it is difficult to directly analyze the original vibration signal to detect the fault. This article proposes a fault diagnosis method combining wavelet packet decomposition (WPD) and Radial Basis Function (RBF) neural network. The wavelet packet decomposition is used to divide the fault signals into multiple frequency bands and then exact the energy of every bands. After the fault features are exacted, the RBF neural network takes the fault signal features as input and inputs their corresponding failure modes. Using bearing data set from Case Western Reserve University to carry out the simulation experiment, the results show that the proposed method can accurately classify rolling bearing faults.