Motor bearing fault detection based on the second generation wavelet theory

In this paper, the second generation wavelet transform and envelope demodulation method combining solve motor bearing fault diagnosis. Firstly, the bearing vibration signal is decomposed into three layers by the second generation wavelet packet transform with predicted and updater. Then We reconstruct the signal which has faulty characteristics. and we demodulate Coefficients largest energy band to get fault characteristic frequency by Hibert envelope. The method can determine the correct motor bearing fault characteristic frequency components, thereby increasing the bearing fault detection. Experimental results show the effectiveness of this method.