Incipient Fault Detection of CRH Suspension system Based on PRPCA and Wasserstein Distance

As an important part of CRH(China Railway High-speed) trains, the stability and stationarity of a suspension system is of great significance to the vehicle system. Based on the framework of probability relevant principal component analysis(PRPCA), a novel data-driven based incipient fault detection method is proposed. Firstly, simulation data including fault information is derived from Simpack-Matlab/Simulink co-simulation platform. Secondly, the real-time monitoring of high-speed train suspension system is proposed based on PRPCA theory combined with wasserstein distance. Furthermore, compared with the traditional PCA based fault detection and diagnosis (FDD) methods, the proposed PRPCA-based method has a better performance and is more suitable for actual fault data has nonlinear and non-Gaussian characteristics. Finally, according to the comparison results with other multivariate statistical analysis based methods, the incipient fault detection method proposed in this paper has a higher sensitivity to the incipient spring/damping faults of CRH suspension system.