Rail wear and remaining life prediction using meta-models

Research output: Contribution to journalArticleAcademicpeer-review

14 Downloads (Pure)

Abstract

The study presented in this paper proposes a method to estimate the Remaining Useful Life (RUL) of railway tracks determined by wear and taking into account various track geometry and usage profile parameters. The relation between these parameters and rail wear is established by means of meta-models derived from physical models. These models are obtained with regression analysis where the best fit is found from a relatively large set of numerical experiments for various scenarios. The specific parameter settings for these scenarios are obtained by using the Latin Hypercube Sampling (LHS) method. Furthermore, for the rail profile, which is one of the input parameters for the meta-model, it is shown that the evolution due to wear in moderate curves can be characterized by only one parameter. The findings in this work including are valuable for Infrastructure Managers (IMs) and can easily be implemented in maintenance decision support tools.
Original languageEnglish
Number of pages26
JournalInternational Journal of Rail Transportation
DOIs
Publication statusE-pub ahead of print/First online - 2 Jun 2019

Fingerprint

Rails
Wear of materials
scenario
Regression analysis
Managers
Sampling
German Federal Railways
regression analysis
Geometry
mathematics
manager
infrastructure
experiment
Experiments

Keywords

  • Wear
  • Wheel-rail contact
  • Multi-body dynamic simulation
  • Meta-modeling
  • Latin hypercube sampling

Cite this

@article{1365e46e694143f2a5e94e1b267f61f0,
title = "Rail wear and remaining life prediction using meta-models",
abstract = "The study presented in this paper proposes a method to estimate the Remaining Useful Life (RUL) of railway tracks determined by wear and taking into account various track geometry and usage profile parameters. The relation between these parameters and rail wear is established by means of meta-models derived from physical models. These models are obtained with regression analysis where the best fit is found from a relatively large set of numerical experiments for various scenarios. The specific parameter settings for these scenarios are obtained by using the Latin Hypercube Sampling (LHS) method. Furthermore, for the rail profile, which is one of the input parameters for the meta-model, it is shown that the evolution due to wear in moderate curves can be characterized by only one parameter. The findings in this work including are valuable for Infrastructure Managers (IMs) and can easily be implemented in maintenance decision support tools.",
keywords = "Wear, Wheel-rail contact, Multi-body dynamic simulation, Meta-modeling, Latin hypercube sampling",
author = "Annemieke Meghoe and Richard Loendersloot and Tiedo Tinga",
year = "2019",
month = "6",
day = "2",
doi = "10.1080/23248378.2019.1621780",
language = "English",
journal = "International Journal of Rail Transportation",
issn = "2324-8378",
publisher = "Taylor & Francis",

}

TY - JOUR

T1 - Rail wear and remaining life prediction using meta-models

AU - Meghoe, Annemieke

AU - Loendersloot, Richard

AU - Tinga, Tiedo

PY - 2019/6/2

Y1 - 2019/6/2

N2 - The study presented in this paper proposes a method to estimate the Remaining Useful Life (RUL) of railway tracks determined by wear and taking into account various track geometry and usage profile parameters. The relation between these parameters and rail wear is established by means of meta-models derived from physical models. These models are obtained with regression analysis where the best fit is found from a relatively large set of numerical experiments for various scenarios. The specific parameter settings for these scenarios are obtained by using the Latin Hypercube Sampling (LHS) method. Furthermore, for the rail profile, which is one of the input parameters for the meta-model, it is shown that the evolution due to wear in moderate curves can be characterized by only one parameter. The findings in this work including are valuable for Infrastructure Managers (IMs) and can easily be implemented in maintenance decision support tools.

AB - The study presented in this paper proposes a method to estimate the Remaining Useful Life (RUL) of railway tracks determined by wear and taking into account various track geometry and usage profile parameters. The relation between these parameters and rail wear is established by means of meta-models derived from physical models. These models are obtained with regression analysis where the best fit is found from a relatively large set of numerical experiments for various scenarios. The specific parameter settings for these scenarios are obtained by using the Latin Hypercube Sampling (LHS) method. Furthermore, for the rail profile, which is one of the input parameters for the meta-model, it is shown that the evolution due to wear in moderate curves can be characterized by only one parameter. The findings in this work including are valuable for Infrastructure Managers (IMs) and can easily be implemented in maintenance decision support tools.

KW - Wear

KW - Wheel-rail contact

KW - Multi-body dynamic simulation

KW - Meta-modeling

KW - Latin hypercube sampling

U2 - 10.1080/23248378.2019.1621780

DO - 10.1080/23248378.2019.1621780

M3 - Article

JO - International Journal of Rail Transportation

JF - International Journal of Rail Transportation

SN - 2324-8378

ER -