Prediction of Track Deterioration Using Maintenance Data and Machine Learning Schemes
Publication: Journal of Transportation Engineering, Part A: Systems
Volume 144, Issue 9
Abstract
The maintenance and renewal of ballasted track can be optimized in terms of time and cost if a proper statistical model of track deterioration is derived from previous maintenance history and measurement data. In this regard, quite a few models with simplified assumptions on the parameters have been suggested for the deterioration of ballasted track. Meanwhile, data driven models such as the artificial neural network (ANN) and support vector regression (SVR), which are basic ingredients of machine learning (ML) technology, were introduced in this study to better represent the deterioration phenomena of track segments so that the results can be directly plugged into the optimization schemes. For this purpose, the influential parameters of track deterioration have been selected based on the maintenance history, and two ML models have been studied to find the best combination of input parameters. Through numerical experiments, it was found that at least 2 years of maintenance data were needed in our case to obtain a stable prediction of track deterioration.
Get full access to this article
View all available purchase options and get full access to this article.
Acknowledgments
This research was funded and supported by the Ministry of Land, Infrastructure and Transport, South Korea, under a grant entitled “Development of the high speed track measurement system for railway maintenance”. The authors are also grateful to Prof. Lin for his helpful suggestion on the LIBSVM.
References
Barmada, S., M. Raugi, M. Tucci, and F. Romano. 2014. “Arc detection in pantograph-catenary systems by the use of support vector machines-based classification.” IET Electr. Syst. Transp. 4 (2): 45–52. https://doi.org/10.1049/iet-est.2013.0003.
Bergmeir, C., G. Sainz, C. Bertrand, and J. Benitez. 2013. “A study on the use of machine learning methods for incidence prediction in high-speed train tracks.” In Vol. 7906 of Proc., IEA/AIE, LNAI, 674–683.
Caetano, L. P., and P. F. Teixeira. 2016. “Predictive maintenance model for ballast tamping.” J. Transp. Eng. 142 (4): 04016006. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000825.
Cardenas-Gallo, I., C. A. Sarmiento, G. A. Morales, and M. A. Bolivar. 2017. “An ensemble classifier to predict track geometry degradation.” Reliab. Eng. Syst. Saf. 161 (May): 53–60. https://doi.org/10.1016/j.ress.2016.12.012.
Chang, C.-C., and C.-J. Lin. 2011. “LIBSVM: A library for support vector machines.” ACM Trans. Intell. Syst. Technol. 2 (3): 1–27. https://doi.org/10.1145/1961189.1961199.
Fumeo, E., L. Oneto, and D. Anguita. 2015. “Condition based maintenance in railway transportation systems based on big data streaming analysis.” Procedia Comput. Sci. 53: 437–446. https://doi.org/10.1016/j.procs.2015.07.321.
Fuqing, Y. 2011. “Failure diagnostics using support vector machine.” Ph.D. thesis, Div. of Operation and Maintenance Engineering, Lulea Univ. of Technology.
Gibert, X., V. Patel, and R. Chellappa. 2015. “Robust fastener detection for autonomous visual railway track inspection.” In Proc., IEEE Winter Conf. Applications of Computer Visualization, 694–701. New York: IEEE.
Guler, H. 2013. “Prediction of railway track geometry deterioration using artificial neural networks: A case study for Turkish state railways.” Struct. Infrastruct. Eng. 10 (5): 614–626. https://doi.org/10.1080/15732479.2012.757791.
Guler, H. 2016. “Optimisation of railway track maintenance and renewal works by genetic algorithms.” Gradevinar 68 (12): 979–993. https://doi.org/10.14256/JCE.1458.2015.
Hagan, M. T., H. B. Demuth, M. H. Beale, and O. De Jesus. 2012. “Neural network design.” Accessed October 9, 2017. http://hagan.okstate.edu/nnd.html.
Hu, C., and X. Liu. 2016. “Modeling track geometry degradation using support vector machine technique.” In Proc., Joint Rail Conf. New York: ASME.
Jovanovic, S. 2006. “Railway track quality assessment and related decision making.” In Proc., AREMA, 202–230. Louisville, KY.
Kang, T. K. 2014. “Optimal maintenance technique of the ballasted track in high-speed railway.” [In Korean.] Ph.D. thesis, Chungnam National Univ.
Karlaftis, M., and E. Vlahogianni. 2011. “Statistical methods versus neural networks in transportation research: Differences, similarities and some insights.” Transp. Res. C 19 (3): 387–399. https://doi.org/10.1016/j.trc.2010.10.004.
Kerr, A. D. 2003. Fundamentals of railway track engineering. Omaha, NE: Simmons-Boardman Books.
Lee, J., I. Choi, I. Kim, and S. Hwang. 2018. “Tamping and renewal optimization of ballasted track using track measurement data and genetic algorithm.” J. Transp. Eng. A. 144 (3): 04017081. https://doi.org/10.1061/JTEPBS.0000120.
Li, D., A. Meddah, K. Hass, and S. Kalay. 2006. “Relating track geometry to vehicle performance using neural network approach.” Proc. Inst. Mech. Eng. F 220 (3): 273–281. https://doi.org/10.1243/09544097JRRT39.
Li, H., D. Parikh, Q. He, B. Qian, Z. Li, D. Fang, and A. Hampapur. 2014. “Improving rail network velocity: A machine learning approach to preventive maintenance.” Transp. Res. C 45 (Aug): 17–26. https://doi.org/10.1016/j.trc.2014.04.013.
Lovett, A. 2017. “Railroad decision support tools for track maintenance.” Ph.D. thesis, Univ. of Illinois.
Sadeghi, J., and H. Askarinejad. 2007. “Influences of track structure, geometry and traffic parameters on railway deterioration.” IJE Trans. B 20 (3): 291–300.
Sadeghi, J., and H. Askarinejad. 2012. “Application of neural networks in evaluation of railway track quality condition.” J. Mech. Sci. Tech. 26 (1): 113–122. https://doi.org/10.1007/s12206-011-1016-5.
Shafahi, Y., P. Masoudi, and R. Hakhamaneshi. 2008. “Track degradation prediction models, using Markov chain, artificial neural and neuro-fuzzy network.” In Proc., 8th WCRR. Zürich, Switzerland: ITA.
Smola, A. J., and B. Scholkopf. 2004. “A tutorial on support vector regression.” Stat. Comput. 14 (3): 199–222. https://doi.org/10.1023/B:STCO.0000035301.49549.88.
Sollazzo, G., T. F. Fwa, and G. Bosurgi. 2017. “An ANN model to correlate roughness and structural performance in asphalt pavements.” Constr. Build. Mater. 134 (Mar): 684–693. https://doi.org/10.1016/j.conbuildmat.2016.12.186.
Tabatabaee, N., M. Ziyadi, and Y. Shafahi. 2013. “Two-stage support vector classifier and recurrent neural network predictor for pavement performance modeling.” J. Infrastruct. Syst. 19 (3): 266–274. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000132.
UIC (Union Internationale des Chemins de Fer). 1992. Factors affecting track maintenance costs and their relative importance. UIC Code 715 R. Paris: UIC.
UIC (Union Internationale des Chemins de Fer). 2009. Classification of lines for the purpose of track maintenance. UIC Code 714 R. Paris: UIC.
Vileiniskis, M., R. Remenyte-Prescott, and D. Rama. 2015. “A fault detection method for railway point systems.” Proc. Inst. Mech. Eng. F. 230 (3): 852–865. https://doi.org/10.1177/0954409714567487.
Woldemariam, W., J. Myrillo-Hoyos, and S. Labi. 2016. “Estimating annual maintenance expenditures for infrastructure: Artificial neural network approach.” J. Infrastruct. Syst. 22 (2): 04015025. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000280.
Information & Authors
Information
Published In
Journal of Transportation Engineering, Part A: Systems
Volume 144 • Issue 9 • September 2018
Copyright
©2018 American Society of Civil Engineers.
History
Received: Oct 22, 2017
Accepted: Mar 20, 2018
Published online: Jun 20, 2018
Published in print: Sep 1, 2018
Discussion open until: Nov 20, 2018
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.