The incipient fault feature enhancement method of the gear box based on the wavelet packet and the minimum entropy deconvolution

Abstract

The amplitude of the vibration signal in the gearbox of the motor driving system is low, resulting in disturbance and vibration noise effect, especially in the early stage of failure. So, it is difficult to extract the characterization of gearbox fault correctly. A method of incipient fault feature enhancement based on the wavelet packet and the minimum entropy deconvolution (MED) is proposed. Firstly, the vibration signal of the gear box containing the incipient fault is decomposed by the wavelet packet, and the decomposed band is reconstructed to eliminate the noise component which is the initial enhancement of the fault feature. After that theMED is used to filter the reconstructed band blind deconvolution to eliminate the influence of the transmission path, so that the feature components of the fault are enhanced again. The combination of WP and MED weakens the influence of the normal components in the original signal, highlights the impact component of the fault, and fully excavates the hidden fault information in the frequency band after the wavelet packet decomposition. Finally, the experimental results are compared and analysed. The experimental results show that the incipient fault feature extracted by this method improves the accuracy of fault diagnosis.

Keywords

• Fault diagnosis
• systems identification and signal processing
• wavelet transforms
• theory-methods
• time series analysis
• systems identification and signal processing