Carbon emission reduction in railway maintenance using reinforcement learning

Jessada Sresakoolchai; Sakdirat Kaewunruen

doi:10.1201/9781003323020

Carbon emission reduction in railway maintenance using reinforcement learning

Jessada Sresakoolchai, Sakdirat Kaewunruen

Civil Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

37 Downloads (Pure)

Abstract

At present, the effect of global warming becomes more severe due to carbon emissions. This negative effect attracts the interest of the international community to minimize it. The railway industry is an industry in which carbon emission cannot be neglected due to the sizes of projects, long operation and maintenance stages in the service life, including sources of energy that might not be clean in some areas. This study aims to minimize the negative effect of the railway industry on the maintenance aspect by using reinforcement learning to optimize maintenance activities. The maintenance in the railway industry is a complicated task and might not be optimized in terms of cost efficiency, serviceability, and environmental impact. The use of reinforcement learning can improve the overall efficiency of railway maintenance as it has been proven in many tasks in the railway industry and other industries. Data used to develop the machine learning model are based on field data collected during 2016-019. The length of the studies section is 30 km. Sources of data are from track geometry cars, maintenance reports, defect reports, and maintenance manuals of the sampled railway operator. The methodology used in the study is Proximal Policy Optimization (PPO). The results show that the use of reinforcement learning can reduce the carbon emission from railway maintenance activities by 48% which causes a significant amount of carbon emission while the railway defects are reduced by 68% which improved maintenance efficiency.

Original language	English
Title of host publication	Life-cycle of structures and infrastructure systems
Subtitle of host publication	Proceedings of the eighth international symposium on life-cycle civil engineering (IALCCE 2023), 2-6 July, 2023, Politecnico Di Milano, Milan, Italy
Editors	Fabio Biondini, Dan M. Frangopol
Place of Publication	London
Publisher	Taylor & Francis
Pages	1778-17785
Number of pages	8
Edition	1
ISBN (Electronic)	9781003323020
DOIs	https://doi.org/10.1201/9781003323020
Publication status	E-pub ahead of print - 28 Jun 2023
Event	Eighth International Symposium on Life-Cycle Civil Engineering: IALCCE 2023 - Milan, Milan, Italy Duration: 2 Jul 2023 → 6 Jul 2023 https://ialcce2023.org/

Publication series

Name	Life-Cycle of Civil Engineering Systems
Publisher	Routledge
ISSN (Electronic)	2641-2195

Conference

Conference	Eighth International Symposium on Life-Cycle Civil Engineering
Abbreviated title	IALCCE 2023
Country/Territory	Italy
City	Milan
Period	2/07/23 → 6/07/23
Internet address	https://ialcce2023.org/

Bibliographical note

ACKNOWLEDGMENT
The authors also wish to thank the European Commission for the financial sponsorship of the H2020-RISE Project no.691135 “RISEN: Rail Infrastructure Systems Engineering Network”, which enables a global research network that addresses the grand challenge of railway infrastructure resilience and advanced sensing in extreme environments (www.risen2rail.eu).

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1201/9781003323020Licence: Creative Commons: Attribution-NonCommercial-NoDerivs (CC BY-NC-ND)

SresakoolchaiJ2023CarbonFinal published version, 450 KBLicence: Creative Commons: Attribution-NonCommercial-NoDerivs (CC BY-NC-ND)

https://www.taylorfrancis.com/chapters/oa-edit/10.1201/9781003323020-218/carbon-emission-reduction-railway-maintenance-using-reinforcement-learning-sresakoolchai-kaewunruenLicence: Creative Commons: Attribution-NonCommercial-NoDerivs (CC BY-NC-ND)

H2020_RISE_RISEN
Kaewunruen, S. (Principal Investigator)
European Commission - Management Costs, European Commission
1/04/16 → 30/09/21
Project: Research

Cite this

Sresakoolchai, J., & Kaewunruen, S. (2023). Carbon emission reduction in railway maintenance using reinforcement learning. In F. Biondini, & D. M. Frangopol (Eds.), Life-cycle of structures and infrastructure systems: Proceedings of the eighth international symposium on life-cycle civil engineering (IALCCE 2023), 2-6 July, 2023, Politecnico Di Milano, Milan, Italy (1 ed., pp. 1778-17785). (Life-Cycle of Civil Engineering Systems). Taylor & Francis. Advance online publication. https://doi.org/10.1201/9781003323020

Sresakoolchai, Jessada ; Kaewunruen, Sakdirat. / Carbon emission reduction in railway maintenance using reinforcement learning. Life-cycle of structures and infrastructure systems: Proceedings of the eighth international symposium on life-cycle civil engineering (IALCCE 2023), 2-6 July, 2023, Politecnico Di Milano, Milan, Italy. editor / Fabio Biondini ; Dan M. Frangopol. 1. ed. London : Taylor & Francis, 2023. pp. 1778-17785 (Life-Cycle of Civil Engineering Systems).

@inproceedings{4e9abe46844a4eaf9ac170f8d2edab73,

title = "Carbon emission reduction in railway maintenance using reinforcement learning",

abstract = "At present, the effect of global warming becomes more severe due to carbon emissions. This negative effect attracts the interest of the international community to minimize it. The railway industry is an industry in which carbon emission cannot be neglected due to the sizes of projects, long operation and maintenance stages in the service life, including sources of energy that might not be clean in some areas. This study aims to minimize the negative effect of the railway industry on the maintenance aspect by using reinforcement learning to optimize maintenance activities. The maintenance in the railway industry is a complicated task and might not be optimized in terms of cost efficiency, serviceability, and environmental impact. The use of reinforcement learning can improve the overall efficiency of railway maintenance as it has been proven in many tasks in the railway industry and other industries. Data used to develop the machine learning model are based on field data collected during 2016-019. The length of the studies section is 30 km. Sources of data are from track geometry cars, maintenance reports, defect reports, and maintenance manuals of the sampled railway operator. The methodology used in the study is Proximal Policy Optimization (PPO). The results show that the use of reinforcement learning can reduce the carbon emission from railway maintenance activities by 48% which causes a significant amount of carbon emission while the railway defects are reduced by 68% which improved maintenance efficiency.",

author = "Jessada Sresakoolchai and Sakdirat Kaewunruen",

note = "ACKNOWLEDGMENT The authors also wish to thank the European Commission for the financial sponsorship of the H2020-RISE Project no.691135 “RISEN: Rail Infrastructure Systems Engineering Network”, which enables a global research network that addresses the grand challenge of railway infrastructure resilience and advanced sensing in extreme environments (www.risen2rail.eu).; Eighth International Symposium on Life-Cycle Civil Engineering : IALCCE 2023, IALCCE 2023 ; Conference date: 02-07-2023 Through 06-07-2023",

year = "2023",

month = jun,

day = "28",

doi = "10.1201/9781003323020",

language = "English",

series = "Life-Cycle of Civil Engineering Systems",

publisher = "Taylor & Francis",

pages = "1778--17785",

editor = "Fabio Biondini and Frangopol, {Dan M.}",

booktitle = "Life-cycle of structures and infrastructure systems",

edition = "1",

url = "https://ialcce2023.org/",

}

Sresakoolchai, J & Kaewunruen, S 2023, Carbon emission reduction in railway maintenance using reinforcement learning. in F Biondini & DM Frangopol (eds), Life-cycle of structures and infrastructure systems: Proceedings of the eighth international symposium on life-cycle civil engineering (IALCCE 2023), 2-6 July, 2023, Politecnico Di Milano, Milan, Italy. 1 edn, Life-Cycle of Civil Engineering Systems, Taylor & Francis, London, pp. 1778-17785, Eighth International Symposium on Life-Cycle Civil Engineering, Milan, Italy, 2/07/23. https://doi.org/10.1201/9781003323020

Carbon emission reduction in railway maintenance using reinforcement learning. / Sresakoolchai, Jessada; Kaewunruen, Sakdirat.
Life-cycle of structures and infrastructure systems: Proceedings of the eighth international symposium on life-cycle civil engineering (IALCCE 2023), 2-6 July, 2023, Politecnico Di Milano, Milan, Italy. ed. / Fabio Biondini; Dan M. Frangopol. 1. ed. London: Taylor & Francis, 2023. p. 1778-17785 (Life-Cycle of Civil Engineering Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Carbon emission reduction in railway maintenance using reinforcement learning

AU - Sresakoolchai, Jessada

AU - Kaewunruen, Sakdirat

N1 - ACKNOWLEDGMENT The authors also wish to thank the European Commission for the financial sponsorship of the H2020-RISE Project no.691135 “RISEN: Rail Infrastructure Systems Engineering Network”, which enables a global research network that addresses the grand challenge of railway infrastructure resilience and advanced sensing in extreme environments (www.risen2rail.eu).

PY - 2023/6/28

Y1 - 2023/6/28

N2 - At present, the effect of global warming becomes more severe due to carbon emissions. This negative effect attracts the interest of the international community to minimize it. The railway industry is an industry in which carbon emission cannot be neglected due to the sizes of projects, long operation and maintenance stages in the service life, including sources of energy that might not be clean in some areas. This study aims to minimize the negative effect of the railway industry on the maintenance aspect by using reinforcement learning to optimize maintenance activities. The maintenance in the railway industry is a complicated task and might not be optimized in terms of cost efficiency, serviceability, and environmental impact. The use of reinforcement learning can improve the overall efficiency of railway maintenance as it has been proven in many tasks in the railway industry and other industries. Data used to develop the machine learning model are based on field data collected during 2016-019. The length of the studies section is 30 km. Sources of data are from track geometry cars, maintenance reports, defect reports, and maintenance manuals of the sampled railway operator. The methodology used in the study is Proximal Policy Optimization (PPO). The results show that the use of reinforcement learning can reduce the carbon emission from railway maintenance activities by 48% which causes a significant amount of carbon emission while the railway defects are reduced by 68% which improved maintenance efficiency.

AB - At present, the effect of global warming becomes more severe due to carbon emissions. This negative effect attracts the interest of the international community to minimize it. The railway industry is an industry in which carbon emission cannot be neglected due to the sizes of projects, long operation and maintenance stages in the service life, including sources of energy that might not be clean in some areas. This study aims to minimize the negative effect of the railway industry on the maintenance aspect by using reinforcement learning to optimize maintenance activities. The maintenance in the railway industry is a complicated task and might not be optimized in terms of cost efficiency, serviceability, and environmental impact. The use of reinforcement learning can improve the overall efficiency of railway maintenance as it has been proven in many tasks in the railway industry and other industries. Data used to develop the machine learning model are based on field data collected during 2016-019. The length of the studies section is 30 km. Sources of data are from track geometry cars, maintenance reports, defect reports, and maintenance manuals of the sampled railway operator. The methodology used in the study is Proximal Policy Optimization (PPO). The results show that the use of reinforcement learning can reduce the carbon emission from railway maintenance activities by 48% which causes a significant amount of carbon emission while the railway defects are reduced by 68% which improved maintenance efficiency.

UR - https://www.routledge.com/Life-Cycle-of-Civil-Engineering-Systems/book-series/IALCCE

U2 - 10.1201/9781003323020

DO - 10.1201/9781003323020

M3 - Conference contribution

T3 - Life-Cycle of Civil Engineering Systems

SP - 1778

EP - 17785

BT - Life-cycle of structures and infrastructure systems

A2 - Biondini, Fabio

A2 - Frangopol, Dan M.

PB - Taylor & Francis

CY - London

T2 - Eighth International Symposium on Life-Cycle Civil Engineering

Y2 - 2 July 2023 through 6 July 2023

ER -

Sresakoolchai J, Kaewunruen S. Carbon emission reduction in railway maintenance using reinforcement learning. In Biondini F, Frangopol DM, editors, Life-cycle of structures and infrastructure systems: Proceedings of the eighth international symposium on life-cycle civil engineering (IALCCE 2023), 2-6 July, 2023, Politecnico Di Milano, Milan, Italy. 1 ed. London: Taylor & Francis. 2023. p. 1778-17785. (Life-Cycle of Civil Engineering Systems). Epub 2023 Jun 28. doi: 10.1201/9781003323020

Carbon emission reduction in railway maintenance using reinforcement learning

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Access to Document

Fingerprint

Projects

H2020_RISE_RISEN

Cite this