Feature extraction method based on parameter optimized Morlet wavelet transform

According to the fact that the defects of mechanical components such as rolling bearing or gearbox can excites vibration with specific impact component, a feature extraction method based on parameter optimized Morlet wavelet is proposed. Firstly, minimum Shannon entropy is used to optimize the Morlet wavelet shape factor in order to match with the impact component. Then, an abrupt information detection method based on the transitional stage of singular curve of wavelet coefficient matrix is used to choose the appropriate scale for the wavelet transformation. Finally, the fault feature of the signal can be extracted using this method. The experimental results and analysis results of rolling bearing signals show that the proposed method could extract fault feature more effectively.