Signalling systems play a major role in railway reliability. However, microcomputer-based monitoring system (MMS), which monitors signal currents, simply raises an alarm when a signal has a failure but cannot recognize the exact reason of the failure. Therefore, we propose an intelligent diagnosis approach to help MMS to recognize faults automatically. First, the approach divides signal current curves collected by MMS into numerous sections with a same length of 600 s. Second, it utilizes dynamic time warping (DTW) to calculate similarities between reference curves and the 600 s-long curves and identify normal ones and a certain type of fault ones named as fluctuant curves. Third, our approach adopts three rules to further distinguish the rest into three types of fault curves. Finally, we conduct an experiment, and the results indicate that our approach can automatically diagnose signal fault curves with 100% accuracy.
Recognition of Signal Fault Curves Based on Dynamic Time Warping for Rail Transportation
Lect. Notes Electrical Eng.
International Conference on Electrical and Information Technologies for Rail Transportation ; 2019 ; Qingdao, China October 25, 2019 - October 27, 2019
Proceedings of the 4th International Conference on Electrical and Information Technologies for Rail Transportation (EITRT) 2019 ; Kapitel : 18 ; 185-195
2020-04-04
11 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Recognition of Signal Fault Curves Based on Dynamic Time Warping for Rail Transportation
British Library Conference Proceedings | 2020
|Turnout Fault Diagnosis through Dynamic Time Warping and Signal Normalization
DOAJ | 2017
|Speech Recognition using Dynamic Time Warping
IEEE | 2008
|