Research on Radial Rotor Plunger Wear Fault Monitoring Method by Fused Sound Vibration Signal Features

The inner curve radial piston motor plunger is easy to wear under radial force. The accuracy of fault identification for wear using a single signal is too low in the influence of fluid flow pulsations. In this article, sound and vibration signals are combined, and the required eigenvalues of the fused signals are extracted based on the feature importance index. The extracted feature values are fused using the Concat method to construct sound and vibration fusion vectors, which are combined with a Light Gradient Boosting Machine (LightGBM) model for training and diagnosis. A hydraulic motor plunger wears fault diagnosis method based on the fusion of vibration and sound signal features recognized by LightGBM is proposed. This method was utilized to analyze simulated plunger wear test data from an inner curve radial piston hydraulic motor test bed. The results show that the diagnostic accuracy using the LightGBM algorithm is improved by 1.35%, 2.21%, and 6.92% over AdaBoost, GBDT, and XGBoost algorithms under the diagnosis of acoustic-vibrational fusion signals, which are affected by the pulsation of liquid flow. The fault diagnosis method based on the fused signals recognized by LightGBM improved the diagnostic accuracy by 4.86% and 14.59%, respectively, compared to the diagnostic results using vibration or sound signals.