Gear Fault Feature Extraction Based on MCKD-VMD

For the difficulty of gear fault extraction in locomotive transmission system, it is easy to be submerged in strong noise. A combination of MCKD-VMD (Maximum Correlated Kurtosis Deconvolution-Modulation Mode Decomposition) is proposed to extract fault features of gears. The method firstly performs correlation function fusion on the collected vibration signals, fuses the signals with higher correlations together, and effectively removes the interference signals; the MCKD method is used to enhance the signals of the fused signals to make the low-frequency signals more obvious; The MCKD enhanced signal is decomposed by VMD to obtain several modal components, and the components with larger correlation coefficients are reconstructed, and power spectrum analysis is performed to identify the fault frequency characteristics of the gear. The denoising performance of the proposed method is better than other methods by the simulation experiment of gear broken teeth. The method is compared with the MCKD-EMD method. The results show that the proposed method can not only suppress the modal aliasing problem, but also more accurate extraction of gear failure frequency and position. It has important practical significance for the early warning of locomotive early warning.