Abstract
The real-time prediction of train movements in time and space is required for ensuring the reliability in operational management and in the information that is relayed to passengers. In practice, however, accurate predictions of train arrival times are very difficult to achieve, given the nature of uncertainty and unpredictability in train movements. This is often due to truly random delay causes that results in a constantly changing probability distribution in delay events as the effects of those causes. The overall consequence is less reliable estimates in train arrival times being made, which can potentially reduce the ability of traffic controllers to effectively plan and respond to disruptions. This paper presents a series of methods that are currently being applied for developing a preliminary working prototype of a future rail advisory system, which is the main objective of an ongoing PhD research project. The system prototype is expected to be capable of relaying advice to a traffic controller with the goal of minimising the effects of a disruption as much as possible and to potentially avoid future disruptions, for which accurate train movement and delay predictions using methods in predictive reasoning and machine learning are vital.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Berger, A., Gebhardt, A., Müller-Hannemann, M., Ostrowski, M.: Stochastic delay prediction in large train newtorks. In: 11th Workshop on Algorithmic Approaches for Transportation Modelling, Optimization and Systems, pp. 100–111 (2011)
Bergström, A., Krüger, N.: Modelling Passenger Train Delay Distributions – Evidence and Implications. Karlstad University Working Paper in Economics, Karlstad University (2013)
Friedman, N., Geiger, D., Goldszmidt, M.: Bayesian network classifiers. Mach. Learn. 29, 131–163 (1997)
Kecman, P., Corman, F., Meng, L.: Train delay evolution as a stochastic process. In: 6th International Conference on Railway Operations Modelling and Analysis, Springer, New York (2015)
Kecman, P., Goverde, R.M.P.: An online railway traffic prediction model. In: 5th International Seminar on Railway Operations Modelling and Analysis. Springer, Berlin (2013)
Keyhani, M.H., Schnee, M., Weihe, K., Zorn, H.P.: Reliability and delay distributions of train connections. In: 12th Workshop on Algorithmic Approaches for Transportation Modelling, Optimization and Systems, pp. 35–46 (2012)
Martin, L., Romanovsky, A., Blewitt, W.: Design and development of train advisory systems for the future. In: 13th International Railway Engineering Conference (2015)
Peng, Z., Lyu, Y., Miller, A., Johnson, C., Zhao, T.: Risk assessment of railway transportation systems using timed fault trees. Qual. Reliab. Eng. Int. (2014)
van Hinsbergen, C.P.I.J., Hegyi, A., van Lint, J.W.C., van Zuylen, H.J.: Bayesian neural networks for the prediction of stochastic travel times in urban networks. IET Intel. Transport Syst. 5(4), 259–265 (2011). doi:10.1049/iet-its.2009.0114
Yaghini, M., Khoshraftar, M.M., Seyedabadi, M.: Railway passenger train delay prediction via neural network model. J. Adv. Transp. 47(3) (2013). doi:10.1002/atr.193
Yuan, J.: Stochastic Modelling of Train Delays and Delay Propagation in Stations. Doctoral thesis, Delft University of Technology, Eburon Academic Publishers (2006)
Network Rail Data Feeds Developer Pack, V2.0, Published by Network Rail. https://odmcr.files.wordpress.com/2012/06/developer-pack-for-network-rail-data-feeds.pdf
Network Rail Strategic Business Plan. Schedule 8. http://www.networkrail.co.uk/browse%20documents/strategicbusinessplan/cp5/supporting%20documents/financing%20and%20funding/schedule%208.pdf
Kang, M.O.: A GA based algorithm for creating energy-optimum train speed trajectory. J. Int. Counc. Electr. Eng. 1(2), 123–128 (2011). doi:10.5370/JICEE.2011.1.2.123
Acknowledgements
This work is sponsored by EPSRC and Siemens Rail Automation within the industrial conversation CASE project on developing train advisory systems of the future. The author would also like to thank Dr. William Blewitt for his advice and feedback and to Newcastle University for their support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Martin, L.J.W. (2016). Predictive Reasoning and Machine Learning for the Enhancement of Reliability in Railway Systems. In: Lecomte, T., Pinger, R., Romanovsky, A. (eds) Reliability, Safety, and Security of Railway Systems. Modelling, Analysis, Verification, and Certification. RSSRail 2016. Lecture Notes in Computer Science(), vol 9707. Springer, Cham. https://doi.org/10.1007/978-3-319-33951-1_13
Download citation
DOI: https://doi.org/10.1007/978-3-319-33951-1_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-33950-4
Online ISBN: 978-3-319-33951-1
eBook Packages: Computer ScienceComputer Science (R0)