No Cover Image

Journal article 73 views 18 downloads

Intelligent Monitoring of Longitudinal Rail Force Using Time Series Forecasting Large Language Models

Hui Yao, Shuo Pan Orcid Logo, Xiaopei Cai, Yi Wang, Hai Yan, Ning Chen, Yuanyuan Hu, Markus Roggenbach Orcid Logo, Clare Wood Orcid Logo, Anand Sreeram Orcid Logo, Yue Hou Orcid Logo

High-speed Railway

Swansea University Authors: Markus Roggenbach Orcid Logo, Clare Wood Orcid Logo, Yue Hou Orcid Logo

  • HSR LLM.pdf

    PDF | Accepted Manuscript

    Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).

    Download (575.4KB)

Check full text

DOI (Published version): 10.1016/j.hspr.2026.05.003

Abstract

High-speed railways constitute a critical component of modern transportation infrastructure. However, the longitudinal rail force, influenced by cyclic train loads and environmental conditions, poses considerable safety risks if not accurately monitored. Traditional longitudinal rail force detection...

Full description

Published in: High-speed Railway
ISSN: 2949-8678
Published: Elsevier BV 2026
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa71994
first_indexed 2026-05-30T11:48:52Z
last_indexed 2026-06-09T08:55:07Z
id cronfa71994
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2026-06-08T13:43:37.9074396</datestamp><bib-version>v2</bib-version><id>71994</id><entry>2026-05-30</entry><title>Intelligent Monitoring of Longitudinal Rail Force Using Time Series Forecasting Large Language Models</title><swanseaauthors><author><sid>7733869ae501442da6926fac77cd155b</sid><ORCID>0000-0002-3819-2787</ORCID><firstname>Markus</firstname><surname>Roggenbach</surname><name>Markus Roggenbach</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>97bede20cc14db118af8abfbb687e895</sid><ORCID>0000-0003-0001-0121</ORCID><firstname>Clare</firstname><surname>Wood</surname><name>Clare Wood</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>92bf566c65343cb3ee04ad963eacf31b</sid><ORCID>0000-0002-4334-2620</ORCID><firstname>Yue</firstname><surname>Hou</surname><name>Yue Hou</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-05-30</date><deptcode>MACS</deptcode><abstract>High-speed railways constitute a critical component of modern transportation infrastructure. However, the longitudinal rail force, influenced by cyclic train loads and environmental conditions, poses considerable safety risks if not accurately monitored. Traditional longitudinal rail force detection techniques primarily rely on physical testing and periodic manual inspections, which significantly limit the potential for real-time and continuous monitoring. To address these limitations, this study introduces an innovative approach employing large language models (LLM) to predict longitudinal rail force based on historical monitoring data. The proposed method is validated through extensive long-term field monitoring of longitudinal rail force on high-speed railway lines, thereby confirming its practical applicability. In contrast to conventional Time Series Forecasting Large Language Models (Time-LLM), the proposed method evaluates the prompt-free architecture. When applied to real-world longitudinal rail force data from the Beijing-Shanghai High-Speed Railway, the model achieves an average coefficient of determination (R2) of 0.932 and a root mean square error (RMSE) of 3.537 kN, outperforming traditional deep learning models. Furthermore, the model exhibits strong robustness under conditions of intermittent data loss. The proposed framework is seamlessly integrated into a localized intelligent system using Langchain-Chatchat, enabling expert-level recommendations based on domain-specific documentation. Overall, this study presents a practical, efficient, and scalable solution for intelligent railway monitoring, offering an advancement toward safer and more intelligent high-speed railway operations.</abstract><type>Journal Article</type><journal>High-speed Railway</journal><volume>0</volume><journalNumber/><paginationStart/><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>2949-8678</issnPrint><issnElectronic/><keywords>High-speed railway; Infrastructure service safety; Long-term monitoring; Artificial intelligence; Deep learning</keywords><publishedDay>26</publishedDay><publishedMonth>5</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-05-26</publishedDate><doi>10.1016/j.hspr.2026.05.003</doi><url/><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm>Other</apcterm><funders>This work was supported by the Natural Science Foundation of Beijing, China (L251029), the Fundamental Research Funds for the Central Universities (2025QYBS007), the National Natural Science Foundation of China (U24A20198).</funders><projectreference/><lastEdited>2026-06-08T13:43:37.9074396</lastEdited><Created>2026-05-30T12:47:02.1611902</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering</level></path><authors><author><firstname>Hui</firstname><surname>Yao</surname><order>1</order></author><author><firstname>Shuo</firstname><surname>Pan</surname><orcid>0000-0001-9452-9738</orcid><order>2</order></author><author><firstname>Xiaopei</firstname><surname>Cai</surname><order>3</order></author><author><firstname>Yi</firstname><surname>Wang</surname><order>4</order></author><author><firstname>Hai</firstname><surname>Yan</surname><order>5</order></author><author><firstname>Ning</firstname><surname>Chen</surname><order>6</order></author><author><firstname>Yuanyuan</firstname><surname>Hu</surname><order>7</order></author><author><firstname>Markus</firstname><surname>Roggenbach</surname><orcid>0000-0002-3819-2787</orcid><order>8</order></author><author><firstname>Clare</firstname><surname>Wood</surname><orcid>0000-0003-0001-0121</orcid><order>9</order></author><author><firstname>Anand</firstname><surname>Sreeram</surname><orcid>0000-0002-3740-9876</orcid><order>10</order></author><author><firstname>Yue</firstname><surname>Hou</surname><orcid>0000-0002-4334-2620</orcid><order>11</order></author></authors><documents><document><filename>71994__36839__2911e66b8953473abcc37c8f3b3e444b.pdf</filename><originalFilename>HSR LLM.pdf</originalFilename><uploaded>2026-05-30T12:48:25.4806711</uploaded><type>Output</type><contentLength>589207</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><documentNotes>Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/deed.en</licence></document></documents><OutputDurs/></rfc1807>
spelling 2026-06-08T13:43:37.9074396 v2 71994 2026-05-30 Intelligent Monitoring of Longitudinal Rail Force Using Time Series Forecasting Large Language Models 7733869ae501442da6926fac77cd155b 0000-0002-3819-2787 Markus Roggenbach Markus Roggenbach true false 97bede20cc14db118af8abfbb687e895 0000-0003-0001-0121 Clare Wood Clare Wood true false 92bf566c65343cb3ee04ad963eacf31b 0000-0002-4334-2620 Yue Hou Yue Hou true false 2026-05-30 MACS High-speed railways constitute a critical component of modern transportation infrastructure. However, the longitudinal rail force, influenced by cyclic train loads and environmental conditions, poses considerable safety risks if not accurately monitored. Traditional longitudinal rail force detection techniques primarily rely on physical testing and periodic manual inspections, which significantly limit the potential for real-time and continuous monitoring. To address these limitations, this study introduces an innovative approach employing large language models (LLM) to predict longitudinal rail force based on historical monitoring data. The proposed method is validated through extensive long-term field monitoring of longitudinal rail force on high-speed railway lines, thereby confirming its practical applicability. In contrast to conventional Time Series Forecasting Large Language Models (Time-LLM), the proposed method evaluates the prompt-free architecture. When applied to real-world longitudinal rail force data from the Beijing-Shanghai High-Speed Railway, the model achieves an average coefficient of determination (R2) of 0.932 and a root mean square error (RMSE) of 3.537 kN, outperforming traditional deep learning models. Furthermore, the model exhibits strong robustness under conditions of intermittent data loss. The proposed framework is seamlessly integrated into a localized intelligent system using Langchain-Chatchat, enabling expert-level recommendations based on domain-specific documentation. Overall, this study presents a practical, efficient, and scalable solution for intelligent railway monitoring, offering an advancement toward safer and more intelligent high-speed railway operations. Journal Article High-speed Railway 0 Elsevier BV 2949-8678 High-speed railway; Infrastructure service safety; Long-term monitoring; Artificial intelligence; Deep learning 26 5 2026 2026-05-26 10.1016/j.hspr.2026.05.003 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University Other This work was supported by the Natural Science Foundation of Beijing, China (L251029), the Fundamental Research Funds for the Central Universities (2025QYBS007), the National Natural Science Foundation of China (U24A20198). 2026-06-08T13:43:37.9074396 2026-05-30T12:47:02.1611902 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering Hui Yao 1 Shuo Pan 0000-0001-9452-9738 2 Xiaopei Cai 3 Yi Wang 4 Hai Yan 5 Ning Chen 6 Yuanyuan Hu 7 Markus Roggenbach 0000-0002-3819-2787 8 Clare Wood 0000-0003-0001-0121 9 Anand Sreeram 0000-0002-3740-9876 10 Yue Hou 0000-0002-4334-2620 11 71994__36839__2911e66b8953473abcc37c8f3b3e444b.pdf HSR LLM.pdf 2026-05-30T12:48:25.4806711 Output 589207 application/pdf Accepted Manuscript true Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention). true eng https://creativecommons.org/licenses/by/4.0/deed.en
title Intelligent Monitoring of Longitudinal Rail Force Using Time Series Forecasting Large Language Models
spellingShingle Intelligent Monitoring of Longitudinal Rail Force Using Time Series Forecasting Large Language Models
Markus Roggenbach
Clare Wood
Yue Hou
title_short Intelligent Monitoring of Longitudinal Rail Force Using Time Series Forecasting Large Language Models
title_full Intelligent Monitoring of Longitudinal Rail Force Using Time Series Forecasting Large Language Models
title_fullStr Intelligent Monitoring of Longitudinal Rail Force Using Time Series Forecasting Large Language Models
title_full_unstemmed Intelligent Monitoring of Longitudinal Rail Force Using Time Series Forecasting Large Language Models
title_sort Intelligent Monitoring of Longitudinal Rail Force Using Time Series Forecasting Large Language Models
author_id_str_mv 7733869ae501442da6926fac77cd155b
97bede20cc14db118af8abfbb687e895
92bf566c65343cb3ee04ad963eacf31b
author_id_fullname_str_mv 7733869ae501442da6926fac77cd155b_***_Markus Roggenbach
97bede20cc14db118af8abfbb687e895_***_Clare Wood
92bf566c65343cb3ee04ad963eacf31b_***_Yue Hou
author Markus Roggenbach
Clare Wood
Yue Hou
author2 Hui Yao
Shuo Pan
Xiaopei Cai
Yi Wang
Hai Yan
Ning Chen
Yuanyuan Hu
Markus Roggenbach
Clare Wood
Anand Sreeram
Yue Hou
format Journal article
container_title High-speed Railway
container_volume 0
publishDate 2026
institution Swansea University
issn 2949-8678
doi_str_mv 10.1016/j.hspr.2026.05.003
publisher Elsevier BV
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering
document_store_str 1
active_str 0
description High-speed railways constitute a critical component of modern transportation infrastructure. However, the longitudinal rail force, influenced by cyclic train loads and environmental conditions, poses considerable safety risks if not accurately monitored. Traditional longitudinal rail force detection techniques primarily rely on physical testing and periodic manual inspections, which significantly limit the potential for real-time and continuous monitoring. To address these limitations, this study introduces an innovative approach employing large language models (LLM) to predict longitudinal rail force based on historical monitoring data. The proposed method is validated through extensive long-term field monitoring of longitudinal rail force on high-speed railway lines, thereby confirming its practical applicability. In contrast to conventional Time Series Forecasting Large Language Models (Time-LLM), the proposed method evaluates the prompt-free architecture. When applied to real-world longitudinal rail force data from the Beijing-Shanghai High-Speed Railway, the model achieves an average coefficient of determination (R2) of 0.932 and a root mean square error (RMSE) of 3.537 kN, outperforming traditional deep learning models. Furthermore, the model exhibits strong robustness under conditions of intermittent data loss. The proposed framework is seamlessly integrated into a localized intelligent system using Langchain-Chatchat, enabling expert-level recommendations based on domain-specific documentation. Overall, this study presents a practical, efficient, and scalable solution for intelligent railway monitoring, offering an advancement toward safer and more intelligent high-speed railway operations.
published_date 2026-05-26T06:02:45Z
_version_ 1868490883398107136
score 11.109323

Similar Items