Research on Degradation State Recognition of Axial Piston Pump under Variable Rotating Speed

Under the condition of variable rotating speed, it is difficult to extract degradation characteristics axial piston pump, which also reduces accuracy recognition. To address these problems, this paper proposes a state recognition method for pumps by combining spline-kernelled chirplet transform (SCT), adaptive chirp mode pursuit (ACMP), and extreme gradient boosting (XGBoost). Firstly, SCT ACMP are proposed deal with vibration signal instability high noise pump under speed. The instantaneous frequency (IF) can be extracted effectively obtaining accurate time-frequency distribution components. Then, stable angular domain signals obtained re-sampling, multi-dimensional from order spectrum. Finally, XGBoost used classify selected recognize state. In paper, in four different states collected analyzed through wear test valve plate pump. Compared pattern algorithms, verified that ensure accuracy.