Fault diagnosis of motor rolling bearing based on IMF sample entropy and particle swarm optimization SVM

Abstract

Aiming at the problem that it is difficult to effectively identify rolling bearing faults, a method for motor rolling bearing faults based on IMF sample entropy and particle swarm optimization SVM (PSO-SVM) is proposed. Firstly, the complementary collective empirical mode decomposition (CEEMD) is applied to the adaptive decomposition of bearing vibration signals to obtain a group of Intrinsic Modal Functions (IMFs). Then the sample entropy of the IMF component containing the main fault feature information was calculated to obtain the sample entropy matrix of the signal component, which was input as the feature vector into the particle swarm optimization SVM for training and testing. Through the analysis of simulation and experimental data, the method has a high identification accuracy for fault types.