Fault diagnosis of rolling bearing based on parameter optimized VMD-FE-SVM

Abstract:
In terms of the non-stationary and non-linear characteristics of rolling bearing vibration signals and the difficulty of feature extraction, a rolling bearing fault feature extraction method based on optimized parameter variational mode decomposition (VMD), fuzzy entropy (FE) and support vector machine (SVM) is proposed. The experimental results show that both VMD-FE and adaptive decomposition can effectively realize the fault diagnosis of rolling bearings. The recognition performance of the method proposed in this paper is slightly better than the feature extraction based on EMD, EEMD, CEEMD and fuzzy entropy, which provides a new idea for the diagnosis of bearing faults.