Document Open Access Logo

A Bayesian Rolling Horizon Approach for Rolling Stock Rotation Planning with Predictive Maintenance

Authors Felix Prause , Ralf Borndörfer

PDF
Thumbnail PDF

File

OASIcs.ATMOS.2024.13.pdf
  • Filesize: 0.76 MB
  • 19 pages

Document Identifiers

Author Details

Felix Prause
  • Zuse Institute Berlin, Germany
Ralf Borndörfer
  • Zuse Institute Berlin, Germany

Funding

This work was supported by the innovation funding program ProFIT (grant no. 10186617), funded by the State of Berlin and co-funded by the European Union.

Cite AsGet BibTex

Felix Prause and Ralf Borndörfer. A Bayesian Rolling Horizon Approach for Rolling Stock Rotation Planning with Predictive Maintenance. In 24th Symposium on Algorithmic Approaches for Transportation Modelling, Optimization, and Systems (ATMOS 2024). Open Access Series in Informatics (OASIcs), Volume 123, pp. 13:1-13:19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
https://doi.org/10.4230/OASIcs.ATMOS.2024.13

Abstract

We consider the rolling stock rotation planning problem with predictive maintenance (RSRP-PdM), where a timetable given by a set of trips must be operated by a fleet of vehicles. Here, the health states of the vehicles are assumed to be random variables, and their maintenance schedule should be planned based on their predicted failure probabilities. Utilizing the Bayesian update step of the Kalman filter, we develop a rolling horizon approach for RSRP-PdM, in which the predicted health state distributions are updated as new data become available. This approach reduces the uncertainty of the health states and thus improves the decision-making basis for maintenance planning. To solve the instances, we employ a local neighborhood search, which is a modification of a heuristic for RSRP-PdM, and demonstrate its effectiveness. Using this solution algorithm, the presented approach is compared with the results of common maintenance strategies on test instances derived from real-world timetables. The obtained results show the benefits of the rolling horizon approach.

Subject Classification

ACM Subject Classification
  • Applied computing → Transportation
  • Mathematics of computing → Bayesian computation
  • Mathematics of computing → Mathematical optimization
Keywords
  • Rolling stock rotation planning
  • Predictive maintenance
  • Rolling horizon approach
  • Bayesian inference
  • Local neighborhood search

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
    0
    Metadata Views

References

  1. Dawn An, Nam H. Kim, and Joo-Ho Choi. Practical options for selecting data-driven or physics-based prognostics algorithms with reviews. Reliability Engineering & System Safety, 133:223-236, 2015. URL: https://doi.org/10.1016/j.ress.2014.09.014.
  2. Javier Andrés, Luis Cadarso, and Ángel Marín. Maintenance scheduling in rolling stock circulations in rapid transit networks. Transportation Research Procedia, 10:524-533, 2015. URL: https://doi.org/10.1016/j.trpro.2015.09.006.
  3. Jeff Bezanson, Alan Edelman, Stefan Karpinski, and Viral B. Shah. Julia: A fresh approach to numerical computing. SIAM review, 59(1):65-98, 2017. URL: https://doi.org/10.1137/141000671.
  4. Ralf Borndörfer, Markus Reuther, Thomas Schlechte, Kerstin Waas, and Steffen Weider. Integrated optimization of rolling stock rotations for intercity railways. Transportation Science, 50(3):863-877, 2016. URL: https://doi.org/10.1287/trsc.2015.0633.
  5. Omar Bougacha, Christophe Varnier, and Noureddine Zerhouni. Impact of decision horizon on post-prognostics maintenance and missions scheduling: a railways case study. International Journal of Rail Transportation, 10(4):516-546, 2022. URL: https://doi.org/10.1080/23248378.2021.1940329.
  6. Valentina Cacchiani, Alberto Caprara, and Paolo Toth. A fast heuristic algorithm for the train unit assignment problem. In 12th Workshop on Algorithmic Approaches for Transportation Modelling, Optimization, and Systems. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2012. URL: https://doi.org/10.4230/OASIcs.ATMOS.2012.1.
  7. Nan Chen and Kwok Leung Tsui. Condition monitoring and remaining useful life prediction using degradation signals: Revisited. IiE Transactions, 45(9):939-952, 2013. URL: https://doi.org/10.1080/0740817X.2012.706376.
  8. Jean-François Cordeau, François Soumis, and Jacques Desrosiers. Simultaneous assignment of locomotives and cars to passenger trains. Operations research, 49(4):531-548, 2001. URL: https://doi.org/10.1287/opre.49.4.531.11226.
  9. Narjes Davari, Bruno Veloso, Gustavo de Assis Costa, Pedro Mota Pereira, Rita P. Ribeiro, and João Gama. A survey on data-driven predictive maintenance for the railway industry. Sensors, 21(17):5739, 2021. URL: https://doi.org/10.3390/s21175739.
  10. Luigi de Simone, Enzo Caputo, Marcello Cinque, Antonio Galli, Vincenzo Moscato, Stefano Russo, Guido Cesaro, Vincenzo Criscuolo, and Giuseppe Giannini. Lstm-based failure prediction for railway rolling stock equipment. Expert Systems with Applications, 222:119767, 2023. URL: https://doi.org/10.1016/j.eswa.2023.119767.
  11. André Listou Ellefsen, Emil Bjørlykhaug, Vilmar Æsøy, Sergey Ushakov, and Houxiang Zhang. Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture. Reliability Engineering & System Safety, 183:240-251, 2019. URL: https://doi.org/10.1016/j.ress.2018.11.027.
  12. Frank Emmert-Streib and Matthias Dehmer. Introduction to survival analysis in practice. Machine Learning and Knowledge Extraction, 1(3):1013-1038, 2019. URL: https://doi.org/10.3390/make1030058.
  13. Aurora Esteban, Amelia Zafra, and Sebastian Ventura. Data mining in predictive maintenance systems: A taxonomy and systematic review. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 12(5):e1471, 2022. URL: https://doi.org/10.1002/widm.1471.
  14. Yuan Gao, Jun Xia, Andrea D’Ariano, and Lixing Yang. Weekly rolling stock planning in chinese high-speed rail networks. Transportation Research Part B: Methodological, 158:295-322, 2022. URL: https://doi.org/10.1016/j.trb.2022.02.005.
  15. Nagi Z. Gebraeel and Mark A. Lawley. A neural network degradation model for computing and updating residual life distributions. IEEE Transactions on Automation Science and Engineering, 5(1):154-163, 2008. URL: https://doi.org/10.1109/TASE.2007.910302.
  16. Nagi Z. Gebraeel, Mark A. Lawley, Rong Li, and Jennifer K. Ryan. Residual-life distributions from component degradation signals: A bayesian approach. IiE Transactions, 37(6):543-557, 2005. URL: https://doi.org/10.1080/07408170590929018.
  17. Giovanni Luca Giacco, Andrea D’Ariano, and Dario Pacciarelli. Rolling stock rostering optimization under maintenance constraints. Journal of Intelligent Transportation Systems, 18(1):95-105, 2014. URL: https://doi.org/10.1080/15472450.2013.801712.
  18. Boris Grimm, Ralf Borndörfer, Markus Reuther, and Thomas Schlechte. A cut separation approach for the rolling stock rotation problem with vehicle maintenance. In 19th Symposium on Algorithmic Approaches for Transportation Modelling, Optimization, and Systems (ATMOS 2019). Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2019. URL: https://doi.org/10.4230/OASIcs.ATMOS.2019.1.
  19. Gurobi Optimization, LLC. Gurobi Optimizer Reference Manual, Version 10.0.2. https://www.gurobi.com, 2024.
  20. Nathalie Herr, Jean-Marc Nicod, Christophe Varnier, Noureddine Zerhouni, and Pierre Dersin. Predictive maintenance of moving systems. In 2017 Prognostics and System Health Management Conference (PHM-Harbin), pages 1-6. IEEE, 2017. URL: https://doi.org/10.1109/PHM.2017.8079111.
  21. Satoshi Kato, Naoto Fukumura, Susumu Morito, Koichi Goto, and Narumi Nakamura. A mixed integer linear programming approach to a rolling stock rostering problem with splitting and combining. In RailNorrköping 2019. 8th International Conference on Railway Operations Modelling and Analysis (ICROMA), Norrköping, Sweden, June 17th-20th, 2019, pages 548-564. Linköping University Electronic Press, 2019. Google Scholar
  22. Yaguo Lei, Naipeng Li, Liang Guo, Ningbo Li, Tao Yan, and Jing Lin. Machinery health prognostics: A systematic review from data acquisition to rul prediction. Mechanical systems and signal processing, 104:799-834, 2018. URL: https://doi.org/10.1016/j.ymssp.2017.11.016.
  23. Hongfei Li, Dhaivat Parikh, Qing He, Buyue Qian, Zhiguo Li, Dongping Fang, and Arun Hampapur. Improving rail network velocity: A machine learning approach to predictive maintenance. Transportation Research Part C: Emerging Technologies, 45:17-26, 2014. URL: https://doi.org/10.1016/j.trc.2014.04.013.
  24. Pin Lim, Chi Keong Goh, Kay Chen Tan, and Partha Dutta. Estimation of remaining useful life based on switching kalman filter neural network ensemble. In Annual Conference of the PHM Society, volume 6(1), 2014. URL: https://doi.org/10.36001/phmconf.2014.v6i1.2348.
  25. Richard M. Lusby, Jørgen Thorlund Haahr, Jesper Larsen, and David Pisinger. A branch-and-price algorithm for railway rolling stock rescheduling. Transportation Research Part B: Methodological, 99:228-250, 2017. URL: https://doi.org/10.1016/j.trb.2017.03.003.
  26. Kursat Rasim Mestav, Jaime Luengo-Rozas, and Lang Tong. State estimation for unobservable distribution systems via deep neural networks. In 2018 IEEE Power & Energy Society General Meeting (PESGM), pages 1-5. IEEE, 2018. URL: https://doi.org/10.1109/PESGM.2018.8586649.
  27. Roberto Nappi, Gianluca Cutrera, Antonio Vigliotti, and Giuseppe Franzè. A predictive-based maintenance approach for rolling stocks vehicles. In 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), volume 1, pages 793-798. IEEE, 2020. URL: https://doi.org/10.1109/ETFA46521.2020.9212183.
  28. Weiwen Peng, Zhi-Sheng Ye, and Nan Chen. Bayesian deep-learning-based health prognostics toward prognostics uncertainty. IEEE Transactions on Industrial Electronics, 67(3):2283-2293, 2019. URL: https://doi.org/10.1109/TIE.2019.2907440.
  29. Felix Prause. A multi-swap heuristic for rolling stock rotation planning with predictive maintenance. In Proceedings of the 11th International Network Optimization Conference (INOC), Dublin, Ireland, March 11-23, 2024, pages 58-63, 2024. URL: https://doi.org/10.48786/inoc.2024.11.
  30. Felix Prause and Ralf Borndörfer. Construction of a test library for the rolling stock rotation problem with predictive maintenance. Technical Report 23-20, ZIB, Takustr. 7, 14195 Berlin, 2023. Google Scholar
  31. Felix Prause, Ralf Borndörfer, Boris Grimm, and Alexander Tesch. Approximating rolling stock rotations with integrated predictive maintenance. Journal of Rail Transport Planning & Management, 30:100434, 2024. URL: https://doi.org/10.1016/j.jrtpm.2024.100434.
  32. Markus Reuther. Mathematical optimization of rolling stock rotations. PhD thesis, Technische Universität Berlin (Germany), 2017. URL: https://doi.org/10.14279/depositonce-5865.
  33. Rita P. Ribeiro, Pedro Pereira, and João Gama. Sequential anomalies: a study in the railway industry. Machine Learning, 105:127-153, 2016. URL: https://doi.org/10.1007/s10994-016-5584-6.
  34. Pegah Rokhforoz and Olga Fink. Hierarchical multi-agent predictive maintenance scheduling for trains using price-based approach. Computers & Industrial Engineering, 159:107475, 2021. URL: https://doi.org/10.1016/j.cie.2021.107475.
  35. Bhaskar Saha, Kai Goebel, Scott Poll, and Jon Christophersen. Prognostics methods for battery health monitoring using a bayesian framework. IEEE Transactions on instrumentation and measurement, 58(2):291-296, 2008. URL: https://doi.org/10.1109/TIM.2008.2005965.
  36. Simo Särkkä and Lennart Svensson. Bayesian filtering and smoothing, volume 17. Cambridge university press, 2023. Google Scholar
  37. Shiliang Sun. A review of deterministic approximate inference techniques for bayesian machine learning. Neural Computing and Applications, 23:2039-2050, 2013. URL: https://doi.org/10.1007/s00521-013-1445-4.
  38. Per Thorlacius, Jesper Larsen, and Marco Laumanns. An integrated rolling stock planning model for the copenhagen suburban passenger railway. Journal of Rail Transport Planning & Management, 5(4):240-262, 2015. URL: https://doi.org/10.1016/j.jrtpm.2015.11.001.
  39. Meng-Ju Wu and Yung-Cheng Lai. Train-set assignment optimization with predictive maintenance. In RailNorrköping 2019. 8th International Conference on Railway Operations Modelling and Analysis (ICROMA), Norrköping, Sweden, June 17th-20th, 2019, pages 1131-1139. Linköping University Electronic Press, 2019. Google Scholar
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact