Application of Wavelet Packet Sample Entropy in the Forecast of Rolling Element Bearing Fault Trend

Abstract

Application of wavelet packet sample entropy in the forecast of rolling element bearing fault trend is proposed in this paper. Firstly, the concept of wavelet packet sample entropy is given. And it illustrates that EMD can better extract the signal trend through the simulation signal. And then the wavelet packet sample entropy for data of the whole life cycle bearing test rig is calculated and the trend of this wavelet packet sample entropy sequence is extracted using EMD. This method could better forecast the operating state of rolling element bearing. So the method of wavelet packet sample entropy and EMD can be used as a good tool for bearing monitoring and forecasting.