Rolling bearing fault diagnosis based on variational mode decomposition and permutation entropy

Abstract

A novel method of fault diagnosis for rolling bearing based on variational mode decomposition (VMD). permutation entropy (PE), and support vector machine (SVM) is put forward in this paper. Firstly, the original vibration signals of bearings are adaptively decomposed into a series of band-limited intrinsic mode function (BUMF) components using VMD. Considering the reason that the permutation entropy can quantify the complexity of the signals to some extent, then permutation entropy is used to extract the feature information of the obtained BLIMF components and the feature vectors could be constructed. Finally, the feature vectors are fed into the SVM classifier to achieve automatic condition identification. The experimental data analysis results demonstrate that the proposed method could be applied to distinguish the different working conditions of rolling bearings. Simultaneously, the comparison results showed that the performance of the proposed method outperforms that of the method based on empirical mode decomposition (EMD) and PE.