Fault Diagnosis of Rolling Bearing Based on EEMD and Optimized SVM

Abstract

In the diagnosis identification of rolling bearing, it is difficult to extract the fault feature and the parameter optimization algorithm of support vector machine (SVM) generally has the problem of slow convergence speed and easy to fall into local optimal solution. Therefore, this paper proposes a method based on ensemble empirical mode decomposition (EEMD) and optimized SVM for the fault diagnosis of rolling bearings. First, EEMD method is used to decompose the rolling bearing signal into several IMF components, and the energy of the components that can reflect the main features of the signal is selected as the feature vector. Then, surface-simplex swarm evolution algorithm is used to optimize the structural parameters of the SVM. Finally, the feature vector set is input into the optimized SVM for the fault diagnosis of the rolling bearing. Experiments show that the method can converge to the optimal solution more quickly and realize the signal diagnosis more accurately.