Research On Performance Degradation Assessment Method Of Hydraulic Pump Based On VMD And SVDD

Hydraulic pump is the power source of the hydraulic system,its health directly affects the normal operation of whole mechanical equipment,so it is very important to monitor the running state and assess the performance degradation degree of the hydraulic pump.Based on the hydraulic pump as the research object,this paper studies the hydraulic pump performance degradation assessment method.Before performance degradation assessment,it is necessary to analyze the nonlinear and non-stationary signals,and extract the features of the signals.In this paper,a feature extraction method based on Variational Mode Decomposition(VMD)and Support Vector Data Description(SVDD)is proposed.Use the capacity that VMD can adaptively decompose the signal into different frequency components and the ability of SVDD outlier detection,extract the singular values of different frequency components as feature vectors,which could reflect the energy distribution of different frequency components.Moreover,this method can make full use of the signal and avoid the interference of noise and other abnormal signals in the signal.After the feature vectors are obtained,use SVDD to assess the performance degradation,the degree of performance degradation is described by the distance from the test sample to the center of hypersphere model.The size and the change of the distance index are different for different equipments or different faults,so the membership function is used to transform the distance index into membership degree as the performance degradation index,unified select different performance degradation index ranges for different performance degradation degrees,and use the bearing data of the whole life published by the university of Cincinnati to verify the effectiveness of the proposed method.Finally,seven groups of vibration signals of axial piston pump are obtained by experiment,they are normal state,three degrees of sliding shoe wear and three degrees of loose boot.Using the comprehensive assessment method based on SVDD to assess the performance degradation of sliding shoe wear and loose boot.Then compared with the traditional time-domain index feature extraction method,the superiority of the proposed method is verified.