Optimizing Maintenance Decision in Rails: A Markov Decision Process Approach
Publication: ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
Volume 7, Issue 1
Abstract
The present paper contributes on how to model maintenance decision support for the rail components, namely on grinding and renewal decisions, by developing a framework that provides an optimal decision map. A Markov decision process (MDP) approach is followed to derive an optimal policy that minimizes the total costs over an infinite horizon depending on the different condition states of the rail. A practical example is explored with the estimation of the Markov transition matrices (MTMs) and the corresponding cost/reward vectors. The MDP states are defined in terms of rail width, height, accumulated million gross tons (MGT) and damage occurrence. The optimal policy represents a condition-based maintenance plan with the aim of supporting railway infrastructure managers to take the best maintenance decision among a set of three possible actions depending on the state of the rail. Overall, the optimal policy requires railway infrastructure companies to have a tight control over their assets, in particular railway lines, in order to constantly monitor the actual condition of the rails.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request:
•
Wear records;
•
Damage records;
•
MATLAB code for Markov transition matrices (MTMs); and
•
MATLAB code for reward vectors.
Acknowledgments
The authors would like to thank the support of Infraestruturas de Portugal, the Portuguese railway infrastructure company, namely, Eng. Marco Baldeiras, for the availability and for providing all information that was used for the present research work. This work is supported by the Foundation for Science and Technology (FCT), through IDMEC, under LAETA, project UIDB/50022/2020. The second author thanks the support of both the FCT and the European Social Fund (ESF), of the European Union (EU), through a Ph.D. scholarship SFRH/BD/147638/2019. The third author expresses his gratitude to the FCT through SFRH/BSAB/150396/2019.
References
Alemazkoor, N., C. J. Ruppert, and H. Meidani. 2018. “Survival analysis at multiple scales for the modeling of track geometry deterioration.” Proc. Inst. Mech. Eng., Part F: J. Rail Rapid Transit 232 (3): 842–850. https://doi.org/10.1177/0954409717695650.
Andrade, A. R., and P. F. Teixeira. 2015. “Statistical modelling of railway track geometry degradation using Hierarchical Bayesian models.” Reliab. Eng. Syst. Saf. 142: 169–183. https://doi.org/10.1016/j.ress.2015.05.009.
Andrade, A. R., and P. F. Teixeira. 2016. “Exploring different alert limit strategies in the maintenance of railway track geometry.” J. Transp. Eng. 142 (9): 04016037. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000867.
Bai, L., R. Liu, Q. Sun, F. Wang, and P. Xu. 2015. “Markov-based model for the prediction of railway track irregularities.” Proc. Inst. Mech. Eng., Part F: J. Rail Rapid Transit 229 (2): 150–159. https://doi.org/10.1177/0954409713503460.
Bevan, A., P. Molyneux-Berry, S. Mills, A. Rhodes, and D. Ling. 2013. “Optimisation of wheelset maintenance using whole-system cost modeling.” Proc. Inst. Mech. Eng., Part F: J. Rail Rapid Transit 227 (6): 594–608. https://doi.org/10.1177/0954409713484712.
Braga, J. A. P., and A. R. Andrade. 2019. “Optimizing maintenance decisions in railway wheelsets: A Markov decision process approach.” Proc. Inst. Mech. Eng., Part O: J. Risk Reliab. 233 (2): 285–300. https://doi.org/10.1177/1748006X18783403.
Brkić, R., and Z. Adamović. 2011. “Research of defects that are related with reliability and safety of railway transport system.” Russ. J. Nondestr. Test. 47 (6): 420–429. https://doi.org/10.1134/S1061830911060040.
BSI (British Standard Institution). 2017. Railway applications—Track—Rail. Part 1: Vignole railway rails and above. EN 13674-1:2011+A1:2017. London: BSI.
Chadès, I., G. Chapron, M. J. Cros, F. Garcia, and R. Sabbadin. 2014. “MDPtoolbox: A multi-platform toolbox to solve stochastic dynamic programming problems.” Ecography 37 (9): 916–920. https://doi.org/10.1111/ecog.00888.
Costa, M. A., J. A. P. Braga, and A. R. Andrade. 2020. “Assessing the performance of different devices in railway wheelset inspection.” Measurement 165: 108145. https://doi.org/10.1016/j.measurement.2020.108145.
Cuervo, P. A., J. F. Santa, and A. Toro. 2015. “Correlations between wear mechanisms and rail grinding operations in a commercial railroad.” Tribol. Int. 82: 265–273. https://doi.org/10.1016/j.triboint.2014.06.025.
Esveld, C. 2001. Modern railway track. 2nd ed. Zaltbommel, Netherlands: MRT Productions.
Famurewa, S. M., L. Zhang, and M. Asplund. 2017. “Maintenance analytics for railway infrastructure decision support.” J. Q. Maint. Eng. 23 (3): 310–325. https://doi.org/10.1108/JQME-11-2016-0059.
Galván-Núñez, S., and N. Attoh-Okine. 2018. “A threshold-regression model for track geometry degradation.” Proc. Inst. Mech. Eng., Part F: J. Rail Rapid Transit 232 (10): 2456–2465. https://doi.org/10.1177/0954409718777834.
Jamshidi, A., S. F. Roohi, A. Núñez, R. Babuska, B. D. Schutter, R. Dollevoet, and Z. Li. 2016. “Probabilistic defect-based risk assessment approach for rail failures in railway infrastructure.” IFAC-PapersOnLine 49 (3): 73–77. https://doi.org/10.1016/j.ifacol.2016.07.013.
Jiang, Z., D. Banjevic, E. Mingcheng, and B. Li. 2017. “Optimizing the re-profiling policy regarding metropolitan train wheels based on a semi-Markov decision process.” Proc. Inst. Mech. Eng., Part O: J. Risk Reliab. 231 (5): 495–507. https://doi.org/10.1177/1748006X17710816.
Kleinbaum, D. G., and M. Klein. 2012. Survival analysis: A self-learning text. 3rd ed. New York: Springer.
Lasisi, A., and N. Attoh-Okine. 2019. “Machine learning ensembles and rail defects prediction: Multilayer stacking methodology.” ASCE-ASME J. Risk Uncertainty Eng. Syst., Part A: Civ. Eng. 5 (4): 04019016. https://doi.org/10.1061/AJRUA6.0001024.
Liu, Y. M., T. Y. Yang, Z. He, and J. Y. Li. 2018. “Analytical modeling of grinding process in rail profile correction considering grinding pattern.” Arch. Civ. Mech. Eng. 18 (2): 669–678. https://doi.org/10.1016/j.acme.2017.10.009.
Madanat, S., K. Smilowitz, and A. Lago. 1999. “Optimal inspection and maintenance policies for infrastructure systems: Facility and network problems.” Transp. Res. Rec. 1667 (1): 1–7. https://doi.org/10.3141/1667-01.
Mingcheng, E., B. Li, Z. Jiang, and Q. Li. 2018. “An optimal reprofiling policy for high-speed train wheels subject to wear and external shocks using a semi-Markov decision process.” IEEE Trans. Reliab. 67 (4): 1468–1481. https://doi.org/10.1109/TR.2018.2870276.
Murthy, D. N. P., M. Xie, and R. Jiang. 2004. Weibull models. Hoboken, NJ: Wiley.
Prescott, D., and J. Andrews. 2015. “Investigating railway track asset management using a Markov analysis.” Proc. Inst. Mech. Eng., Part F: J. Rail Rapid Transit 229 (4): 402–416. https://doi.org/10.1177/0954409713511965.
Puterman, M. L. 1995. Markov decision processes: Discrete stochastic dynamic programming. New York: Wiley.
REFER (National Railway Network). 2009. Tolerâncias de desgaste do perfil transversal do carril. IT.VIA.021. Lisbon, Portugal: REFER.
Shafahi, Y., and R. Hakhamaneshi. 2009. “Application of a maintenance management model for Iranian railways based on the Markov chain and probabilistic dynamic programming.” Sci. Iranica 16 (1): 87–97.
Sharma, S., Y. Cui, Q. He, R. Mohammadi, and Z. Li. 2018. “Data-driven optimization of railway maintenance for track geometry.” Transp. Res. Part C: Emerging Technol. 90: 34–58. https://doi.org/10.1016/j.trc.2018.02.019.
Sheskin, T. J. 2011. Markov chains and decision processes for engineers and managers. 1st ed. Boca Raton, FL: CRC Press.
Tutcher, J., J. M. Easton, and C. Roberts. 2017. “Enabling data integration in the rail industry using RDF and OWL: The RaCoOn ontology.” ASCE-ASME J. Risk Uncertainty Eng. Syst., Part A: Civ. Eng. 3 (2): F4015001. https://doi.org/10.1061/AJRUA6.0000859.
Xie, M., and C. D. Lai. 1996. “Reliability analysis using an additive Weibull model with bathtub-shaped failure rate function.” Reliab. Eng. Syst. Saf. 52 (1): 87–93. https://doi.org/10.1016/0951-8320(95)00149-2.
Zakeri, J.-A., and S. Shahriari. 2012. “Developing a deterioration probabilistic model for rail.” Int. J. Traffic Transp. Eng. 1 (2): 13–18. https://doi.org/10.5923/j.ijtte.20120102.02.
Information & Authors
Information
Published In
ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
Volume 7 • Issue 1 • March 2021
Copyright
© 2020 American Society of Civil Engineers.
History
Received: Mar 29, 2020
Accepted: Aug 17, 2020
Published online: Nov 23, 2020
Published in print: Mar 1, 2021
Discussion open until: Apr 23, 2021
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.