Fault Feature Extraction of Rolling Bearings Based on Variational Mode Decomposition and Singular Value Entropy

Abstract

In order to solve the problem that the fault characteristic signals of rolling bearings are weak and the fault identification is relatively difficult, a fault feature extraction method for rolling bearings based on variational mode decomposition singular value entropy is proposed. The original signals are decomposed by variational mode decomposition, and some intrinsic modal functions are obtained to form the initial characteristic matrix. Then, the singular value decomposition technique is used to process the initial characteristic matrix and the singular value entropy is obtained by combining the information entropy theory. Finally, according to the magnitude of the singular value entropy, the working states and fault types of rolling bearings are distinguished. The results show that this method can classify the weak faults of rolling bearings more clearly and has higher fault identification accuracy.