Fault Diagnosis of Gearbox based on Singular Spectrum and Redundant Lifting Wavelet Analysis

Gearbox is the key component of power equipment such as coal mill,its fault has a great impact on the normal operation of equipment. The early fault signal of the bearing is weak and often submerged by the noise signal,so how to remove the noise and extract the fault feature signal is the key to realize the fault diagnosis of equipment. At present,the research of wavelet analysis is mainly based on the determination of wavelet function and the selection of threshold to analysis the effect of noise reduction,the determination of decomposition levels has not been thoroughly resolved. The singular spectrum analysis method and the redundant lifting wavelet method are combined to solve the problem of how to determine the number of decomposition layers in wavelet analysis,which greatly improves the performance of the method. The reliability of this method is verified by analyzing the actual signals of a gearbox of a coal mill in a power plant. The application of this method provides the help for the timely and accurate identification and detection of the fault diagnosis.