VMD based adaptive multiscale fuzzy entropy and its application to rolling bearing fault diagnosis

摘要

Based on the recently proposed method for nonlinear and non-stationary vibration signal, variational mode decomposition (VMD), an adaptive multiscale fuzzy entropy (AMFE) method is introduced in this paper. Firstly, the VMD method is used to decompose the vibration signals of rolling bearing into a number of intrinsic mode functions (IMFs). Then the fuzzy entropy of each IMF is computed. Meanwhile, combining with support vector machine (SVM), a new rolling bearing fault diagnosis approach is put forward. The proposed method is applied to the experimental data of rolling bearing and the analysis results show the effectiveness of the proposed method.