Railway track intervention planning is the process of specifying the location and time of required maintenance and renewal activities. To facilitate the process, decision support tools have been developed and typically use an expert system built with rules specified by track maintenance engineers. However, due to the complex interrelated nature of component deterioration, it is problematic for an engineer to consider all combinations of possible deterioration mechanisms using a rule based approach. To address this issue, this chapter describes an approach to the intervention planning using a variety of computational intelligence techniques. The proposed system learns rules for maintenance planning from historical data and incorporates future data to update the rules as they become available thus the performance of the system improves over time. To determine the failure type, historical deterioration patterns of sections of track are first analyzed. A Rival Penalized Competitive Learning algorithm is then used to determine possible failure types. We have devised a generalized two stage evolutionary algorithm to produce curve functions for this purpose. The approach is illustrated using an example with real data which demonstrates that the proposed methodology is suitable and effective for the task in hand.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Association of Train Operating Companies (2006), Ten-Year European Rail Growth Trends, The Association of Train Operating Companies, London, UK., 1 July 2006
Burrow, M.P.N., Ghataora, G.S & Bowness, D. (2004), Analytical track substructure design. ISSMGE TC3 International Seminar on Geotechnics in Pavement and Railway Design and Construction, NTUA - Athens, 16-17 December 2004., pp. 209–216
Cheung, Y. (2004), A Competitive and Cooperative Learning Approach to Robust Data Clustering, IASTED International Coference on Neural Networks and Computational Intelligence, 23-25 February 2004, pp. 131–136
Cope, G.H.(1993), British Railway Track — Design, Construction and Maintenance, The Permanent Way Institution, Eco Press. Loughborough, UK., 1993
Coulouris, G.F., Dollimore, J. & Kindberg, T. (2000), Distributed Systems: Concepts and Design, Third Edition. International Computer Science, 23 August 2000, pp. 28–64
ERRI (1994), EcoTrack - Decision Support System for Permanent Way Maintenance and Renewal - Specifications 1. General Concept, ERRI, April 1994
Esveld, C. (2001), Modern Railway Track, Second Edition. MRT-Productions, Zaltbommel, The Netherlands., August 2001
Jovanovic, S. (2000), Optimal Resource Allocation Within the Field of Railway Track Maintenance and Renewal, Railway Engineering 2000, London, 5-6 July 2000.
Jovanovic, S. & Esveld, C. (2001), An Objective Condition-based Decision Support System for Long-term Track Maintenance and Renewal Planning, 7th International Heavy Haul Conference, Australia, 10-14 June 2001, pp. 199–207
Jovanovic, S. & Zaalberg, H. (2000), EcoTrack - Two Years of Experience, Rail International, April 2000, pp. 2–8
King, I. & Lau, T. (1999), Non-Hierarchical Clustering with Rival Penalized Competitive Learning for Information Retrieval, First International Workshop on Machine Learning and Data Mining in Pattern Recognition, 16-18 September 1999, pp. 116-130
Leeuwen, R.V. (1996), The EcoTrack Project - Effective Management of Track Maintenance, Belgium National Railway Company, Brussels, 1996, pp. 1–16
Moore, A.W. (2004), K-means and Hierarchical Clustering, Carnegie Mellon University, 8 October 2004.
Network Rail (2006), Business Plan, Network Rail, UK., 4 April 2006
Stirling, A.B., Roberts, C.M., Chan, A.H.C., Madelin, K.B. & Bocking, A. (1999), Development of a Rule Base (Code of Practice) for the Maintenance of Plain Line Track in the UK to be used in an Expert System, Railway Engineering 1999, London, 26-27 May 1999
Stirling, A.B., Roberts, C.M., Chan, A.H.C., Madelin, K.B. & Vernon, K. (2000), Trial of an Expert System for the Maintenance of Plain Line Track in the UK, Railway Engineering 2000, London, 5-6 July 2000
Stirling, A.B., Roberts, C.M., Chan, A.H.C. & Madelin, K.B. (2000), Prototype Expert System for the Maintenance and Renewal of Railway Track, Freight Vehicle Design Workshop, Manchester, 2000
Rivier, R. & Korpanec, I. (1997), EcoTrack - A Tool to Reduce the Life Cycle Costs of the Track, World Congress on Railway Research, 16-19 November 1997, pp. 289–295
Rivier, R.E. (1998), EcoTrack - A Tool for Track Maintenance and Renewal Managers, Computational Mechanics Publications, Institute of Transportation and Planning, Swiss Federal, September 1998, pp. 733–742
Roberts, C. (2001), A Decision Support System for Effective Track Maintenance and Renewal, PhD Thesis, The University of Birmingham, January 2001
Roberts, C. (2001), Decision Support System for Track Renewal Strategies and Maintenance Optimization, Railway Engineering 2001, 30 April-1 May 2001
Zaa, P.H. (1998), Economizing Track Renewal and Maintenance with EcoTrack, Cost Effectiveness and Safety Aspects of Railway Track, Paris, 1998
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Bartram, D., Burrow, M., Yao, X. (2008). A Computational Intelligence Approach to Railway Track Intervention Planning. In: Yu, T., Davis, L., Baydar, C., Roy, R. (eds) Evolutionary Computation in Practice. Studies in Computational Intelligence, vol 88. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75771-9_8
Download citation
DOI: https://doi.org/10.1007/978-3-540-75771-9_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-75770-2
Online ISBN: 978-3-540-75771-9
eBook Packages: EngineeringEngineering (R0)