A fault diagnosis method for the tuning area of jointless track circuits based on a neural network

Abstract

This paper proposes a fault diagnosis method for the tuning area of jointless track circuits (JTCs) that is based on using a neural network. Based on the basic structure and working principle of a JTC and track circuit reader (TCR), the induced voltage amplitude envelope (IVAE) in a TCR under different typical fault modes of the tuning area is modelled using transmission line theory. Then, a quadratic function is used to implement piecewise fitting to the IVAE between the tuning area at the sending end of the track circuit and the fourth compensation capacitor counted from the sending end, for fault feature extraction. On the basis of the feature extracted, a back propagation neural network is constructed and trained for fault diagnosis of the tuning units. Experiments with real data show that this method has many advantages such as high detection accuracy, good adaptability and a wide applied range, etc. It can overcome the disadvantages of the current detection methods in aspects such as detection cost and timeliness. Furthermore, it also improves the safety and efficiency of train operation.

Keywords

Fault diagnosis railways jointless track circuit transmission line theory back propagation neural network

Get full access to this article

View all access options for this article.

References

Chen J, Roberts C and Weston P. Neuro-fuzzy fault detection and diagnosis for railway track circuits. In: The sixth IFAC symposium on fault detection, supervision and safety of technical processes (ed., Zhang Z), Beijing, China, 29 August–1 September 2006, pp. 1366–1371. Australia: IFAC Secretariat.

. Analysis and solutions about off code and interference due to adjacent tracks. Chin Railw 2009; 48(05): 58–61.

Zhao LH, Guo JR, Li H and Liu WN. The simulation analysis of influence on jointless track circuit signal transmission from compensation capacitor based on transmission-line theory. In: The third IEEE international symposium on microwave, antenna, propagation and EMC technologies for wireless communications (ed., Wen YH), Beijing, China, 27–29 October 2009, pp. 1113–1118. Piscataway, NJ: IEEE Press.

Oukhellou

Debiolles

Denoeux

Aknin

. Fault diagnosis in railway track circuits using Dempster–Shafer classifier fusion. Engng Appl Artif Intell 2010; 23(1): 117–128.

Cherfi

Oukhellou

Come

. Partially supervised independent factor analysis using soft labels elicited from multiple experts: application to railway track circuit diagnosis. Soft Comput 2012; 12(5): 741–754.

Gao

. Analysis and countermeasure for interference due to adjacent tracks of ZPW-2000A closed loop coding. Railw Signal Commun 2006; 42(9): 27–27.

Wang

Guan

. Analysis about the safety of ZPW-2000A tuning area minor track circuit. Railw Signal Commun 2005; 41: 12–13.

Kang

Guan

Song

. Study on comprehensive monitoring and control system of train operation safety for Shanghai–Nanjing line. Chin Railw Sci 2002; 23(3): 1–5.

Track inspection car. Baidupedia. 16 April 2008. http://baike.baidu.com/view/1530096.htm (accessed 5 January 2012).

10.

Fei

. Principle and analysis of jointless track circuit, Beijing: China Railway Publishing House, 1993.

11.

Zhao

. Fault diagnosis method for jointless track circuit based on AOK-TFR. J Southwest Jiaotong Univ 2011; 46(1): 84–91.

12.

China Railway Ministry. Railway signal maintenance rules technical standards II, Beijing: China Railway Publishing House, 2008.

13.

Deng

Chen

Liu

. A novel hybrid methodology combining back propagation neural network with rough set and its application. Proc IMechE, Part F: J Rail Rapid Transit 2011; 225(3): 259–265.

14.

Chen

Gao

. Soft computing methods applied to train station parking in urban rail transit. Appl Soft Comput 2012; 12(2): 759–767.

15.

Sadeghi

Askarinejad

. Application of neural networks in evaluation of railway track quality condition. J Mech Sci Technol 2012; 26(1): 113–122.

16.

Cleophas

. Artificial intelligence for diagnostic purposes: principles, procedures and limitations. Clin Chem Lab Med 2010; 48(2): 159–165.

17.

Tsai

Chen

. On the use of temporal reachout technique for characteristics method with time-line cubic spline interpolation. J Mech 2011; 27(2): N5–N11.

18.

Gao

. Research on structures of supervised linear basis function feed-forward three-layered neural networks. Chin J Comput 1998; 21(1): 80–86.

19.

Ding

. An optimizing BP neural network algorithm based on genetic algorithm. Artif Intell Rev 2011; 36(2): 153–162.

20.

Kermani

Schiffman

Nagle

. Performance of the Levenberg–Marquardt neural network training method in electronic nose applications. Sens Actuators B, Chem 2005; 110(1): 13–22.

21.

Kaminski

Orlowska-Kowalska

. Optimisation of neural state variables estimators of two-mass drive system using the Bayesian regularization method. Bull Polish Acad Sci, Tech Sci 2011; 59(1): 33–38.