Rotating Machinery Fault Diagnosis Based on Support Vector Machine

In order to identify the rotating machinery fault, a method based on support vector machine (SVM) is proposed in this paper. After the feature vectors from the fault signals by means of wavelet packet are extracted and the support vector machine (SVM) classification algorithm to the classification of faults in rolling bearing is applied. By drawing a comparison between the classification and BP neural network, the experiment shows that SVM algorithm has a better classification performance than BP neural network among limited fault samples.