Fault Diagnosis of Rotating Equipment Bearings Based on VMD-MSGWO-SVM

In this paper, the bearing fault problem of rotating equipment is studied by using support vector machine (SVM) model classification method. In order to solve the problem of low accuracy of using SVM to detect the fault for bearing, the method of variational mode decomposition (VMD) is introduced to extract features from original vibration data and the intelligent optimization algorithm of MSGWO is introduced to optimize parameters of SVM, which can improve fault diagnosis performance of classification system. A variety of comparative experiments are carried out by using FEMTO-ST bearing data set which is open source on the internet. The results show that the proposed algorithm has high prediction accuracy and is superior to the present methods in classification.