Cost-effective Inspection and Maintenance Rule for Train Control Beacons
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
A substantial part of the French railway network is equipped with ground-based beacons that control train speed. This
“KVB” system (French initials for beacon-based speed control) plays an important role in ensuring train operation safety.
When a beacon is failed, maximum speed compliance over the section where failure occurred is potentially at risk. Therefore,
detecting failed beacons and replacing them in a timely manner but not too often is fundamental to guarantee safe operation of the network while keeping maintenance costs under control. This is accomplished by means of regular commercial trains which detect failed beacons (albeit imperfectly). Upon a number p of successive detections of the same beacon as failed by different trains over a certain period (typically one day), this beacon is signaled as failed to the maintenance control center and is replaced as soon as possible. The question therefore arises of optimizing the signaling rule, i.e., determining the best number p of apparent detections that should trigger a maintenance intervention. Three main contributions are reported in this paper: 1) Determination of steady-state operational availability as a function of the failure rate, the headway, the mean time to restore and the fault detection probability; 2) A method for the optimal choice of the number p in the signaling rule; 3) An algorithm for diagnosing whether a beacon or a train is defective, thereby reducing detection time and false positives. Several sensitivity analyses are also conducted, both of the availability and the total cost,
with respect to the various relevant parameters. Generalization to other train control systems, such as the European-wide
Pierre Dersin et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided
the original author and source are credited. ETCS (European Train Control System) should be straightforward. To the authors’ knowledge, it is the first time that such algorithms for decision optimization under uncertainty are applied in the context of train control system maintenance.
How to Cite
##plugins.themes.bootstrap3.article.details##
availability, maintenance costs, failure detection, optimization, decision support.
Bewick V. Cheek, J., L. Ball. (2004). Statistics review 13: Receiver operating characteristic curve. Critical Care, 8.
Cooper, G. F. (1990). The computational complexity of probabilistic inference using Bayesian belief networks. Artificial
Intelligence, 42(2–3), 393–405.
Ghahramani, Z., & Jordan, M. I. (1997). Factorial hidden markov models. Machine Learning, 1–31.
Koller, D., & Friedman, N. (2009). Probabilistic graphical models: Principles and techniques. MIT Press.
Kschischang, F. R., Frey, B. J., & Loeliger, H.-A. (2001). EUROPEAN CONFERENCE OF THE PROGNOSTICS AND HEALTH MANAGEMENT SOCIETY 2026. Factor graphs and the sum-product algorithm. IEEE Transactions on Information Theory, 47(2), 498–519.
Murphy, K. P., Weiss, Y., & Jordan, M. I. (1999). Loopy belief propagation for approximate inference: An empirical
study. In Proceedings of the fifteenth conference on uncertainty in artificial intelligence (pp. 467–475).
Pearl, J. (1988). Probabilistic reasoning in intelligent systems:Networks of plausible inference. Morgan Kaufmann.
Ross, S. (2010). Introduction to probability models. Elsevier. Sch¨on, W., Benso, J.-N., Larraufie, G., Mo¨ens, G., & Por´e,
J. (2019). Railway signalling and automation (Vol. 3). La Vie du Rail.13
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.