Slow feature analysis-aided detection and diagnosis of incipient faults for running gear systems of high-speed trains. (June 2022)

• Record Type: Journal Article
• Authors: Cheng, Chao; Liu, Ming; Chen, Hongtian; Xie, Pu; Zhou, Yang
• Is Part Of: ISA transactions. Volume 125(2022)
• Page Start: 415
• Page End: 425
• Publication Date: 2022-06
• Subjects: Incipient faults -- Fault detection and diagnosis -- Hellinger distance -- Slow feature analysis -- Hidden Markov methods -- Running gear systems; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2021.06.023
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: Incipient faults in running gear systems corrupt the overall performance of high-speed trains, increasing the necessity of fault detection and diagnosis whose purpose is to maintain the safe and stable operation of high-speed trains. For this purpose, a novel data-driven method, that utilizes Hellinger distance and slow feature analysis, is proposed in this study. By integrating Hellinger distance into slow feature analysis, a new test statistic is defined for detecting incipient faults in running gear systems. Furthermore, the hidden Markov method is developed for performing reliable fault diagnosis tasks. The salient strengths of the proposed method lie in its satisfactory fault detectability on the one hand and the considerable robustness against high-level noises on the other hand. Finally, the effectiveness of the proposed method is verified through a numerical example and a running gear system of high-speed trains under actual working conditions. Highlights: A new data driven method named HSFA is proposed to detect incipient faults of running gear systems. The proposed method has high flexibility, especially when the accurate mathematical models or expert knowledge cannot gain. The robustness of HSFA has great potential.