Method on Fault Detection and Diagnosis for Track Circuit Based on Main Rail Voltage

Abstract:

This paper proposes a method of the fault detection and diagnosis for the railway circuit of ZPW-2000 system based on the main track voltage curve. Exact curve matching fault detection method and SVM-based fault diagnosis method are adopted. Based on envelope algorithm, exact curve matching method is used to match the detected current curve with the reference curve so as to predict whether the curve would have fault or not. Then, the SVM-based fault diagnosis method is used to make sure that the fault classification could be diagnosed intelligently. The experiment results show that the proposed method can accurately identify the track circuit fault state, and the accuracy rate in the diagnosis of the fault location is above 99%, which verify the effectiveness of the method in the fault detection and diagnosis.

• Periodical: Applied Mechanics and Materials (Volumes 670-671)
• Pages: 1172-1178
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.670-671.1172
• Online since: October 2014
• Authors: Da Zhuang Wu, Yu Fang*, Quan Song Ma
• Keywords: Curve Matching, Fault Detection and Diagnosis, Main Rail Voltage Curve of Track Circuit, SVM, ZPW-2000 System

References

[1] Fanglin Huang, Guolong Ma. Modern Railway Transport [M]. China Railway Publishing House, (In Chinese), (2003).

[2] Keyi Huang, PeiDe Wu.  Railway Introduction [M]. China Railway Publishing House , (In Chinese), (1983).

[3] Ying Hu. Study on Track Circuit Fault Diagnosis System of Railway Signal Based on Fuzzy Neural Network [D]. Beijing Jiaotong University, (In Chinese), (2012).

[4] Ruiming Fang. Analysis of Theory and Application of Support Vector Machines [J]. Beijing China Electric Power Press, (In Chinese), 2007-10-01.

[5] Daqi Zhu, Shenglin Yu. Survey of knowledge-based fault diagnosis methods [J]. Journal of Anhui University of Technology (Natural Science). 2002(03).

[6] Shaoxu Ni, Yufang Zhang, Hong Yi, Xiaofeng Liang. Intelligent Fault Diagnosis Method Based on fault Tree [J]. Journal of Shanghai Jiaotong University. (In Chinese), 2008(08).

[7] Gang Tong, Guozhong Zhang, Junming Miao. The Application of Optimizing Neural Network to the Machine Fault Diagnosis on the Genetic Algorithm [J]. Machinery & Electronics. (In Chinese), 2006(06).

[8] Shan Wang, Lvsha Yuan, Weihua Zhang. Fault Diagnosis of Transformer based on BP Neural Network [J]. Heilongjiang Science and Technology Information. (In Chinese), 2011(29).

[9] Wanlu Jiang, Deqiang Wu. Multi-data fusion fault diagnose method based on SVM and evidence theory [J]. Chinese Journal of Scientific Instrument. (In Chinese), 2010(08).

[10] Nello Cristianini, John Shawe-Taylor. An introduction to support vector machines: and other kernel-based learning methods [M]. Beijing: China Machine Press, (2005).

DOI: 10.1017/cbo9780511801389

[11] Ming YAN, Fajie Duan. Research on Recognition Method of Curve Character [J]. Journal of Transduction Technology, (In Chinese), 2006 (03).