Research on Performance Degradation Prediction of Urban Rail Vehicle Suspension System

Along with the rapid development of urban rail transit, the security and reliability of rail transit vehicle system draw more and more attention. Suspension system plays a key role to support the car body, bogies, and wheels; therefore, it is vitally important to implement overall performance attenuation prediction, which can establish the maintenance plan based on the equipment status and reduce the cost. In this paper, a method of performance attenuation prediction about whole urban rail vehicle suspension system is proposed. The performance attenuation prediction model is established by utilizing LSSVR, of which the parameters are optimized based on SPSO. Compared with traditional methods, the SPSO-LSSVR model has higher prediction efficiency and prediction accuracy. In addition, considering the actual application, the prediction effect is analyzed when the vehicle body and bogie acceleration are model inputs, and a comparative study is carried out in the horizontal and vertical directions, which verifies the feasibility of the method used in the field engineering.