Rolling bearing fault diagnosis based on MEEMD sample entropy and SSA-SVM

Abstract

Abstract The penalty parameter (c) and kernel parameter (g) contained in Support Vector Machine (SVM) cannot be adaptively selected according to actual samples, which results in low classification accuracy and slow convergence speed. A novel sparrow search algorithm was used to optimize the parameters of SVM classifier. Firstly, an improved ensemble empirical mode decomposition (MEEMD) method was used to decompose non-stationary and nonlinear vibration signals, and the eigenmode function (IMF) was obtained by removing abnormal signals from the original signals through permutation entropy, and the sample entropy was extracted. Finally, a fault diagnosis model based on SSA-SVM is constructed, and the high recognition rate and effectiveness of this method are proved by simulation and experimental data analysis.