01697340

Component

Turnouts are one of the most crucial infrastructures in railway signal systems, and they significantly influence the safety and efficiency of train operation. Currently, the identification of turnout failures mainly depends on the experience of railway staff and the use of simple thresholding methods. However, these basic methods are highly defective and frequently result in false and missing alarms. This paper aims to develop a segmented similarity-based diagnostic (SSBD) method for railway turnouts. The intelligent process identifies faults based on current curves collected by microcomputer monitoring systems. The authors first divide these current curves into three segments based on the three mechanical processes that occur during turnout operation. Then, a standard curve is selected from fault-free curves, and common typical faults are ascertained through a microcomputer monitoring system.Finally, Gaussian dynamic time warping (GDTW) and a quartile scheme are employed to identify fault curves. An experiment based on current curves collected from the Guangzhou Railway Bureau in China demonstrates that the SSBD method is extremely accurate and has low missing and false alarm rates. Besides, SSBD performs better than the studied dynamic timing warping (DTW), support vector machine (SVM) and artificial neural network (ANN) methods, which are widely used for fault diagnosis.

This paper was sponsored by TRB committee AR030 Standing Committee on Railroad Operating Technologies.

19-00931

English

17p

2019

Transportation Research Board 98th Annual Meeting

Digital/other

Figures; References; Tables

Diagnosis; Fault monitoring; Intelligent control systems; Railroad maintenance facilities; Railroad signals; Railroad turnouts; Railroads

Maintenance and Preservation; Railroads

Transportation Research Board Annual Meeting 2019 Paper #19-00931

TRIS, TRB, ATRI

Dec 7 2018 9:24AM