Multiobjective Optimization for Railway Maintenance Plans

Daniel Peralta, Christoph Bergmeir, Martin Krone, Marta Galende, Manuel Menéndez, Gregorio I. Sainz-Palmero, Carlos Martinez Bertrand, Frank Klawonn, Jose M. Benitez

    Research output: Contribution to journalArticleResearchpeer-review

    Abstract

    Railway track maintenance is a critical problem for any railway administrator. More precisely, preventive maintenance scheduling is a nondeterministic polynomial time (NP)-hard problem, which additionally involves multiple objectives such as economic cost, maximum capacity, serviceability, safety, and passenger comfort. This paper proposes a multiobjective optimization approach to this problem, combined with a track deterioration model that takes into account the degradation caused by maintenance operations. The track behavior is simulated by an exponential deterioration model based on a two-level segmentation. The maintenance schedule is built using a Pareto-based algorithm with two objectives (cost and delay) and three constraints, on top of an initialization heuristic based on expert knowledge. The proposed approach has been tested with two different algorithms (NSGA-II and AMOSA) over a model of a real track to create schedules for different horizons ranging between 3 and 20 years. The solutions obtained by AMOSA outperform those designed by human experts both in terms of time delay and economic cost, demonstrating the capability of the proposal to produce near-optimal long-term maintenance schedules.

    Original languageEnglish
    Article number04018014
    Pages (from-to)1-11
    Number of pages11
    JournalJournal of Computing in Civil Engineering
    Volume32
    Issue number3
    DOIs
    Publication statusPublished - 1 May 2018

    Cite this

    Peralta, D., Bergmeir, C., Krone, M., Galende, M., Menéndez, M., Sainz-Palmero, G. I., ... Benitez, J. M. (2018). Multiobjective Optimization for Railway Maintenance Plans. Journal of Computing in Civil Engineering, 32(3), 1-11. [04018014]. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000757
    Peralta, Daniel ; Bergmeir, Christoph ; Krone, Martin ; Galende, Marta ; Menéndez, Manuel ; Sainz-Palmero, Gregorio I. ; Martinez Bertrand, Carlos ; Klawonn, Frank ; Benitez, Jose M. / Multiobjective Optimization for Railway Maintenance Plans. In: Journal of Computing in Civil Engineering. 2018 ; Vol. 32, No. 3. pp. 1-11.
    @article{6917e34f898d4230a3785e5727df5b3e,
    title = "Multiobjective Optimization for Railway Maintenance Plans",
    abstract = "Railway track maintenance is a critical problem for any railway administrator. More precisely, preventive maintenance scheduling is a nondeterministic polynomial time (NP)-hard problem, which additionally involves multiple objectives such as economic cost, maximum capacity, serviceability, safety, and passenger comfort. This paper proposes a multiobjective optimization approach to this problem, combined with a track deterioration model that takes into account the degradation caused by maintenance operations. The track behavior is simulated by an exponential deterioration model based on a two-level segmentation. The maintenance schedule is built using a Pareto-based algorithm with two objectives (cost and delay) and three constraints, on top of an initialization heuristic based on expert knowledge. The proposed approach has been tested with two different algorithms (NSGA-II and AMOSA) over a model of a real track to create schedules for different horizons ranging between 3 and 20 years. The solutions obtained by AMOSA outperform those designed by human experts both in terms of time delay and economic cost, demonstrating the capability of the proposal to produce near-optimal long-term maintenance schedules.",
    author = "Daniel Peralta and Christoph Bergmeir and Martin Krone and Marta Galende and Manuel Men{\'e}ndez and Sainz-Palmero, {Gregorio I.} and {Martinez Bertrand}, Carlos and Frank Klawonn and Benitez, {Jose M.}",
    year = "2018",
    month = "5",
    day = "1",
    doi = "10.1061/(ASCE)CP.1943-5487.0000757",
    language = "English",
    volume = "32",
    pages = "1--11",
    journal = "Journal of Computing in Civil Engineering",
    issn = "0887-3801",
    publisher = "American Society of Civil Engineers",
    number = "3",

    }

    Peralta, D, Bergmeir, C, Krone, M, Galende, M, Menéndez, M, Sainz-Palmero, GI, Martinez Bertrand, C, Klawonn, F & Benitez, JM 2018, 'Multiobjective Optimization for Railway Maintenance Plans' Journal of Computing in Civil Engineering, vol. 32, no. 3, 04018014, pp. 1-11. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000757

    Multiobjective Optimization for Railway Maintenance Plans. / Peralta, Daniel; Bergmeir, Christoph; Krone, Martin; Galende, Marta; Menéndez, Manuel; Sainz-Palmero, Gregorio I.; Martinez Bertrand, Carlos; Klawonn, Frank; Benitez, Jose M.

    In: Journal of Computing in Civil Engineering, Vol. 32, No. 3, 04018014, 01.05.2018, p. 1-11.

    Research output: Contribution to journalArticleResearchpeer-review

    TY - JOUR

    T1 - Multiobjective Optimization for Railway Maintenance Plans

    AU - Peralta, Daniel

    AU - Bergmeir, Christoph

    AU - Krone, Martin

    AU - Galende, Marta

    AU - Menéndez, Manuel

    AU - Sainz-Palmero, Gregorio I.

    AU - Martinez Bertrand, Carlos

    AU - Klawonn, Frank

    AU - Benitez, Jose M.

    PY - 2018/5/1

    Y1 - 2018/5/1

    N2 - Railway track maintenance is a critical problem for any railway administrator. More precisely, preventive maintenance scheduling is a nondeterministic polynomial time (NP)-hard problem, which additionally involves multiple objectives such as economic cost, maximum capacity, serviceability, safety, and passenger comfort. This paper proposes a multiobjective optimization approach to this problem, combined with a track deterioration model that takes into account the degradation caused by maintenance operations. The track behavior is simulated by an exponential deterioration model based on a two-level segmentation. The maintenance schedule is built using a Pareto-based algorithm with two objectives (cost and delay) and three constraints, on top of an initialization heuristic based on expert knowledge. The proposed approach has been tested with two different algorithms (NSGA-II and AMOSA) over a model of a real track to create schedules for different horizons ranging between 3 and 20 years. The solutions obtained by AMOSA outperform those designed by human experts both in terms of time delay and economic cost, demonstrating the capability of the proposal to produce near-optimal long-term maintenance schedules.

    AB - Railway track maintenance is a critical problem for any railway administrator. More precisely, preventive maintenance scheduling is a nondeterministic polynomial time (NP)-hard problem, which additionally involves multiple objectives such as economic cost, maximum capacity, serviceability, safety, and passenger comfort. This paper proposes a multiobjective optimization approach to this problem, combined with a track deterioration model that takes into account the degradation caused by maintenance operations. The track behavior is simulated by an exponential deterioration model based on a two-level segmentation. The maintenance schedule is built using a Pareto-based algorithm with two objectives (cost and delay) and three constraints, on top of an initialization heuristic based on expert knowledge. The proposed approach has been tested with two different algorithms (NSGA-II and AMOSA) over a model of a real track to create schedules for different horizons ranging between 3 and 20 years. The solutions obtained by AMOSA outperform those designed by human experts both in terms of time delay and economic cost, demonstrating the capability of the proposal to produce near-optimal long-term maintenance schedules.

    UR - http://www.scopus.com/inward/record.url?scp=85043379658&partnerID=8YFLogxK

    U2 - 10.1061/(ASCE)CP.1943-5487.0000757

    DO - 10.1061/(ASCE)CP.1943-5487.0000757

    M3 - Article

    VL - 32

    SP - 1

    EP - 11

    JO - Journal of Computing in Civil Engineering

    JF - Journal of Computing in Civil Engineering

    SN - 0887-3801

    IS - 3

    M1 - 04018014

    ER -