A Feature Extraction Method Using VMD and Improved Envelope Spectrum Entropy for Rolling Bearing Fault Diagnosis

Feature extraction is a key step in intelligent bearing fault diagnosis. However, bearing vibration signals are usually nonlinear, nonstationary signal with strong noises. Extracting the effective status feature of the bearing is challenging. Thus, a new rolling bearing status feature extraction method based on variational mode decomposition (VMD) and improved envelope spectrum entropy (IESE) is proposed in this article. First, the bearing vibrational signals are decomposed into different intrinsic mode functions (IMFs) by VMD. Then, the envelope spectrum entropy (ESE) of each IMF is calculated and the IESE is obtained by reconstructing the ESE to build original feature sets. Finally, the original feature set is fused by the joint approximate diagonalization eigen (JADE) to obtain a new one. The new feature set is trained and tested by using a support vector machine (SVM) to identify the bearing status. The feasibility of the proposed method for feature extraction is verified by three experimental cases. Compared with several methods, the performance of this proposed method is better than those of other methods.