Fault diagnosis of rolling bearing based on wavelet packet frequency-shifting algorithm AR model

The vibration signals of the bearing are typical non-stationary time series, with the wavelet packet frequency-shifting algorithm and autoregressive(AR) model to combine, and the non-stationary can be preferably characterized by establishing their a wavelet packet frequency-shifting algorithm of autoregressive(AR) model. The wavelet packet frequency-shift algorithm AR model parameters can be extracted as the feature vectors of the bearing´s run state, and are input to support vector machine(SVM) classifier to recognize and classify the fault patterns, then the intelligent fault diagnosis is realized. The experiment results show the effectiveness and accuracy of the proposed approach for recognizing the states of rolling bearing.