A fault diagnosis method of rolling bearing based on VMD Tsallis entropy and FCM clustering

Abstract

A new fault diagnosis method of rolling bearings was presented based on variational mode decomposition (VMD), Tsallis entropy and Fuzzy C-means clustering (FCM) algorithm. Firstly, the measured vibration signals were decomposed with VMD in different scales to obtain a series of band-limited intrinsic modal function (BIMF). The VMD parameters were determined according to the change of the BIMF center frequency. Then, the Tsallis entropy of BIMF components were calculated and used as the signal features. Finally, the features were put into FCM classifier to recognize different fault types. It is proved by experiments that this method is feasible and the proposed approach could obtain better result compared with the method based on mode decomposition (EMD) and local mean decomposition (LMD).