Rail Degradation Modelling Using ARMAX: A Case Study Applied to Melbourne Tram System
There is a necessity among rail transportation authorities for a superior understanding of the rail track degradation overtime and the factors influencing rail degradation. They need an accurate technique to identify the time when rail tracks fail or need maintenance. In turn, this will help to increase the level of safety and comfort of the passengers and the vehicles as well as improve the cost effectiveness of maintenance activities. An accurate model can play a key role in prediction of the long-term behaviour of railroad tracks. An accurate model can decrease the cost of maintenance. In this research, the rail track degradation is predicted using an autoregressive moving average with exogenous input (ARMAX). An ARMAX has been implemented on Melbourne tram data to estimate the values for the tram track degradation. Gauge values and rail usage in Million Gross Tone (MGT) are the main parameters used in the model. The developed model can accurately predict the future status of the tram tracks.
Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1132164Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 967
 Y.-J. Zhang, M. H. Murray, and L. Ferreira, “Modelling rail track performance: an integrated approach”, Transport Journal, 2000, pp.187-194.
 Q. He, H. Li, D. Bhattacharjya, D. P. Parikh, and A. Hampapur, “Track geometry defect rectification based on track deterioration modelling and derailment risk assessment,” Journal of the Operational Research Society, vol. 66, 2015, pp. 392-404.
 S. Jovanovic, H. Guler, and B. Coko, “Track degradation analysis in the scope of railway infrastructure maintenance management systems,” Gradevinar, vol. 67, 2015, pp. 247-257.
 A. Iman Soleimanmeigouni, A. Uday Kumar, “Track geometry degradation and maintenance modelling,” A review Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 2016.
 Yarra Trams, Facts and figures, Yarra Trams, Melbourne, 2017.
 B. Lichtberger, Track Compendium, Eurailpress Tetzlaff-Hestra GmbH & CO. KG, 2005.
 C. Esveld, “Modern railway track,” MRT-productions Zaltbommel, The Netherlands, 2001.
 R. Fröhling, “Wheel/rail interface management in heavy haul railway operations—applying science and technology,” Vehicle System Dynamics, vol. 45, 2007, pp. 649-677.
 N. Lyngby, P. Hokstad, and J. Vatn, “RAMS management of railway tracks,” Handbook of performability engineering, Springer, 2008.
 L. Wilson, “Optimization of rail/wheel lubrication,” Doctoral Thesis, Queensland University of Technology, 2006.
 A. R. Andrade, P. F. Teixeira, “Statistical modelling of railway track geometry degradation using Hierarchical Bayesian models,” Reliability Engineering and System Safety, vol. 142, 2015, pp. 169-183.
 J. Bernardo, “Bayesian statistics,” Updated and abridged version of the Chapter ‘Bayesian statistics’ published in Probability and Statistics (R. Viertl, Ed.) of the Encyclopedia of Life Support Systems (EOLSS), Oxford, UK: UNESCO, 2003.
 I. Ntzoufras, “Bayesian modeling in WinBugs,” Hoboken, NJ, USA: John Wiley & Sons, Inc., 2009.
 L. M. Quiroga, E. Schnieder, “Monte Carlo simulation of railway track geometry deterioration and restoration,” Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, vol. 226, 2011, pp. 274-282.
 Y. Shafahi, R. Hakhamaneshi, “Application of a maintenance management model for Iranian railways based on the Markov chain and probabilistic dynamic programming,” International Journal of Science and Technology. Transaction A: Civil Engineering, vol. 16, 2009, pp. 87-97.
 D. Prescott, J. Andrews, “Modelling maintenance in railway infrastructure management,” Reliability and Maintainability Symposium (RAMS), 2013 Proceedings-Annual, 2013, IEEE, pp. 1-6.
 C. Vale, S. M. Lurdes, “Stochastic model for the geometrical rail track degradation process in the Portuguese railway Northern Line,” Reliability Engineering & System Safety, vol. 116, 2013, pp. 91-98.
 H. Guler, “Prediction of railway track geometry deterioration using artificial neural networks: a case study for Turkish state railways,” Structure and Infrastructure Engineering, 2014, pp. 614–626.
 J. Sadeghi, H. Askarinejad, “Application of neural networks in evaluation of railway track quality condition,” Mechanical Science Technology (26), 2012, pp. 113–122.
 Y. Shafahi, P. Masoudi, and R. Hakhamaneshi, “Track Degradation Prediction Models, Using Markov Chain, Artificial Neural and Neuro-Fuzzy Network,” 2008.
 S. Moridpour, R. Hesami, “Degradation and performance specification of Melbourne tram tracks,” International Conference on Transportation Information and Safety (ICTIS), 25-28 June, 2015.
 S. Moridpour, E. Mazloumi, and R. Hesami, “Application of Artificial Neural Networks in Predicting the Degradation of Tram Tracks Using Maintenance Data”, Applied Big Data Analytics in Operations Management. IGI Global, U.S, 2016.
 M. Yousefikia, S. Moridpour, S. Setunge, and E. Mazloumi, “Modeling degradation of tracks for maintenance planning on a tram line,” Engineering and Technology Publishing, U.S, 2014.
 C. Gao, M. Jiang, J. Y. Huang, and X. F. Wang, “Degradation path modeling method based on time series analysis,” Applied Mechanics and Materials, 2012.
 M. Khashei, M. Bijari, “A novel hybridization of artificial neural networks and ARIMA models for time series forecasting,” Applied Soft Computing, vol. 11(2), 2011, pp. 2664-2675.
 A. Samé, F. Chamroukhi, G. Govaert, and P. Aknin, “Model-based clustering and segmentation of time series with changes in regime,” Advances in Data Analysis and Classification, vol. 5(4), 2011, pp. 301-321.
 L. Wang, H. Zhang, and H. Xue, “Life Prediction based on Degradation Amount Distribution using Composite Time Series Analysis,” IERI Procedia, 1, 2012, pp. 217-224.
 A. Wijeweera, H. To, M. B. Charles, and K. Sloan, “A time series analysis of passenger rail demand in major Australian cities,” Economic Analysis and Policy, vol. 44(3), 2014, pp. 301-309.
 G. P. Zhang, “Time series forecasting using a hybrid ARIMA and neural network model,” Neurocomputing, vol. 50, 2003, pp. 159-175.
 O. Nelles, “Nonlinear system identification: from classical approaches to neural networks and fuzzy models,” Springer Science & Business Media, 2013.