Research on SVM Classification Performance in Rolling Bearing Diagnosis

Abstract

SVM are introduced into rolling bearings intelligent fault diagnosis due to the fact that it is hard to obtain enough fault samples in practice and the perfect performance of SVM. The two-class classifier performance of SVM is discussed under the different conditions with the combination of wavelet packet denoising, decomposition and SVM. The performance comparison of SVM and RBF neural networks is presented. The multi-class classification performance of SVM is researched with a novel method of PCA and SVM, and feature extracting is discussed. The experiment and analysis results show that SVM have perfect classified performance in only limited training samples and the diagnosis precision is less dependent on the kernel function and the parameter, which is suitable in the engineering applications. SVM also has better performance than RBF networks both in training speed and recognition rate. PCA method can effectively reduce the calculating complexity of the fault classifier and keep high diagnosis precision. The fault diagnosis method based on PCA and SVM can extract rolling bearing fault features effectively and recognize the fault pattern accurately.