Fault Feature Recognition and Diagnosis of Gear Pump Bearing Based on VMD

Rolling bearing failure is very important to the safe operation and efficient production of mechanical equipment. Aiming at the difficulty of fault feature extraction of gear pump bearings, this paper proposes a fault feature recognition and diagnosis of gear pump bearing based on Variational Mode Decomposition (VMD). First, the optimal penalty factor and IMF number K under different working conditions are found by observation method. Secondly, the time domain signal of the original rolling bearing is decomposed by VMD adaptive decomposition, and an IMF component with a large kurtosis value is found for reconstruction. Finally, the accuracy and effectiveness of VMD for fault feature recognition and diagnosis are proved by the analysis results of simulation signals and experimental signals. The results show that compared with the empirical mode component (EMD) decomposition method, the proposed method can increase the signal-to-noise ratio more effectively, to extract the fault characteristics of gear pump bearing vibration signals.