A Bearing Feature Extraction Method Based on Variational Mode Decomposition Feature Energy Entropy

The fault feature extraction is the critical role of rolling bearing fault diagnosis. This paper has proposed a bearing fault feature extraction method based on variational mode decomposition (VMD) feature energy entropy. The bearing fault signals was decomposed by using VMD, and some IMF components was obtained; Then the corresponding IMF components was selected according to the data or operation state for reconstruction; and the energy entropy value of the reconstructed signal was calculated to diagnose the fault of rolling bearing. The experiment results show that the proposed method can effectively identify rolling bearing fault types, and it can also accurately distinguish fault degrees.