Sensors, Vol. 19, Pages 3981: Wayside Detection of Wheel Minor Defects in High-Speed Trains by a Bayesian Blind Source Separation Method

Sensors, Vol. 19, Pages 3981: Wayside Detection of Wheel Minor Defects in High-Speed Trains by a Bayesian Blind Source Separation Method
Sensors doi: 10.3390/s19183981
Authors:
Xiao-Zhou Liu
Chi Xu
Yi-Qing Ni

For high-speed trains, out-of-roundness (OOR)/defects on wheel tread with small radius deviation may suffice to give rise to severe damage on both vehicle components and track structure when they run at high speeds. It is thus highly desirable to detect the defects in a timely manner and then conduct wheel re-profiling for the defective wheels. This paper presents a wayside fiber Bragg grating (FBG)-based wheel condition monitoring system which can detect wheel tread defects online during train passage. A defect identification algorithm is developed to identify potential wheel defects with the monitoring data of rail strain response collected by the devised system. In view that minor wheel defects can only generate anomalies with low amplitude compared with the wheel load effect, advanced signal processing methods are needed to extract the defect-sensitive feature from the monitoring data. This paper explores a Bayesian blind source separation (BSS) method to decompose the rail response signal and to obtain the component that contains defect-sensitive features. After that, the potential defects are identified by analyzing anomalies in the time history based on the Chauvenet’s criterion. To verify the proposed defect detection method, a blind tes...

Source: Sensors - September 13, 2019 Category: Biotechnology Authors: Xiao-Zhou Liu Chi Xu Yi-Qing Ni Tags: Article Source Type: research