Fault Diagnosis of Rolling Bearing Based on Wavelet Packet Transform and Support Vector Machine

In this paper, fault diagnosis approach to rolling bearing based on wavelet packet transform and support vector machine is proposed. At first, feature vectors are extracted from the non-stationary vibration signals by means of wavelet packet transform. Then support vector machine algorithm is used to fault identification and classification of rolling bearing. The experiments show that, as for limited fault samples, support vector machine classifier has a better classification efficiency than BP neural network classifier.