No Cover Image

Journal article 22 views 7 downloads

Diagnosis of high‐speed railway ballastless track arching based on unsupervised learning framework

Xueyang Tang, Yi Wang, Xiaopei Cai, Fei Yang, Yue Hou Orcid Logo

Computer‐Aided Civil and Infrastructure Engineering

Swansea University Author: Yue Hou Orcid Logo

  • mice.13342.pdf

    PDF | Version of Record

    © 2024 The Author(s). This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License (CC-BY-NC-ND).

    Download (4.85MB)

Check full text

DOI (Published version): 10.1111/mice.13342

Abstract

Vehicle‐mounted detection methods have been widely applied in the maintenance of high‐speed railways (HSRs), providing feasibility for diagnosing ballastless track arching. However, applying detection data faces several key limitations: (1) The threshold mostly requires manual setting, making recogn...

Full description

Published in: Computer‐Aided Civil and Infrastructure Engineering
ISSN: 1093-9687 1467-8667
Published: Wiley 2024
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa67733
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2024-09-19T11:50:14Z
last_indexed 2024-09-19T11:50:14Z
id cronfa67733
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>67733</id><entry>2024-09-19</entry><title>Diagnosis of high‐speed railway ballastless track arching based on unsupervised learning framework</title><swanseaauthors><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>2024-09-19</date><deptcode>ACEM</deptcode><abstract>Vehicle‐mounted detection methods have been widely applied in the maintenance of high‐speed railways (HSRs), providing feasibility for diagnosing ballastless track arching. However, applying detection data faces several key limitations: (1) The threshold mostly requires manual setting, making recognition accuracy highly subjective; (2) the extensive workload of manual inspections makes it challenging to label detection data, hindering the application of supervised learning approaches. To address these problems, this paper utilizes the longitudinal level irregularity data obtained from vehicle‐mounted detection, employing the concept of unsupervised learning for dimensionality reduction, combined with clustering algorithms and minimal label fine‐tuning, to design two frameworks: the fully unsupervised framework (FUF) and the few‐shot fine‐tuned framework (FFF). Experiments on dynamic detection data from a Chinese HSR line were conducted, comparing the performance of data dimensionality reduction, clustering, and classification under different strategy combinations. The results show that the improved variational autoencoder significantly enhances the performance of the encoder in dimensionality reduction, facilitating better feature extraction; the FUF achieves effective clustering outcomes without any labeled samples and its adjusted rand index score exceeded 0.8, showcasing its robustness and applicability in scenarios with no prior annotations; the FFF requires only a small number of labeled samples (labeling ratio of 5%) and achieves excellent performance, with metrics such as accuracy exceeding 0.85, thus greatly reducing the reliance on labeled data. This study offers a novel method for solving engineering issues with limited labeled data, providing an efficient solution for identifying track arching defects and advancing railway infrastructure monitoring.</abstract><type>Journal Article</type><journal>Computer‐Aided Civil and Infrastructure Engineering</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher>Wiley</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1093-9687</issnPrint><issnElectronic>1467-8667</issnElectronic><keywords/><publishedDay>18</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-09-18</publishedDate><doi>10.1111/mice.13342</doi><url/><notes/><college>COLLEGE NANME</college><department>Aerospace, Civil, Electrical, and Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>ACEM</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This research is supported by the National Natural Science Foundation of China No. 52178405, the Fundamental Research Funds for the Central Universities No. 2022JBQY009.</funders><projectreference/><lastEdited>2024-09-19T12:50:33.3726348</lastEdited><Created>2024-09-19T12:38:04.9461914</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>Xueyang</firstname><surname>Tang</surname><order>1</order></author><author><firstname>Yi</firstname><surname>Wang</surname><order>2</order></author><author><firstname>Xiaopei</firstname><surname>Cai</surname><order>3</order></author><author><firstname>Fei</firstname><surname>Yang</surname><order>4</order></author><author><firstname>Yue</firstname><surname>Hou</surname><orcid>0000-0002-4334-2620</orcid><order>5</order></author></authors><documents><document><filename>67733__31383__79fd4f1275004b7d8a39d1f8ea1f58eb.pdf</filename><originalFilename>mice.13342.pdf</originalFilename><uploaded>2024-09-19T12:38:04.9268931</uploaded><type>Output</type><contentLength>5085563</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2024 The Author(s). This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License (CC-BY-NC-ND).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by-nc-nd/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 67733 2024-09-19 Diagnosis of high‐speed railway ballastless track arching based on unsupervised learning framework 92bf566c65343cb3ee04ad963eacf31b 0000-0002-4334-2620 Yue Hou Yue Hou true false 2024-09-19 ACEM Vehicle‐mounted detection methods have been widely applied in the maintenance of high‐speed railways (HSRs), providing feasibility for diagnosing ballastless track arching. However, applying detection data faces several key limitations: (1) The threshold mostly requires manual setting, making recognition accuracy highly subjective; (2) the extensive workload of manual inspections makes it challenging to label detection data, hindering the application of supervised learning approaches. To address these problems, this paper utilizes the longitudinal level irregularity data obtained from vehicle‐mounted detection, employing the concept of unsupervised learning for dimensionality reduction, combined with clustering algorithms and minimal label fine‐tuning, to design two frameworks: the fully unsupervised framework (FUF) and the few‐shot fine‐tuned framework (FFF). Experiments on dynamic detection data from a Chinese HSR line were conducted, comparing the performance of data dimensionality reduction, clustering, and classification under different strategy combinations. The results show that the improved variational autoencoder significantly enhances the performance of the encoder in dimensionality reduction, facilitating better feature extraction; the FUF achieves effective clustering outcomes without any labeled samples and its adjusted rand index score exceeded 0.8, showcasing its robustness and applicability in scenarios with no prior annotations; the FFF requires only a small number of labeled samples (labeling ratio of 5%) and achieves excellent performance, with metrics such as accuracy exceeding 0.85, thus greatly reducing the reliance on labeled data. This study offers a novel method for solving engineering issues with limited labeled data, providing an efficient solution for identifying track arching defects and advancing railway infrastructure monitoring. Journal Article Computer‐Aided Civil and Infrastructure Engineering Wiley 1093-9687 1467-8667 18 9 2024 2024-09-18 10.1111/mice.13342 COLLEGE NANME Aerospace, Civil, Electrical, and Mechanical Engineering COLLEGE CODE ACEM Swansea University This research is supported by the National Natural Science Foundation of China No. 52178405, the Fundamental Research Funds for the Central Universities No. 2022JBQY009. 2024-09-19T12:50:33.3726348 2024-09-19T12:38:04.9461914 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering Xueyang Tang 1 Yi Wang 2 Xiaopei Cai 3 Fei Yang 4 Yue Hou 0000-0002-4334-2620 5 67733__31383__79fd4f1275004b7d8a39d1f8ea1f58eb.pdf mice.13342.pdf 2024-09-19T12:38:04.9268931 Output 5085563 application/pdf Version of Record true © 2024 The Author(s). This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License (CC-BY-NC-ND). true eng http://creativecommons.org/licenses/by-nc-nd/4.0/
title Diagnosis of high‐speed railway ballastless track arching based on unsupervised learning framework
spellingShingle Diagnosis of high‐speed railway ballastless track arching based on unsupervised learning framework
Yue Hou
title_short Diagnosis of high‐speed railway ballastless track arching based on unsupervised learning framework
title_full Diagnosis of high‐speed railway ballastless track arching based on unsupervised learning framework
title_fullStr Diagnosis of high‐speed railway ballastless track arching based on unsupervised learning framework
title_full_unstemmed Diagnosis of high‐speed railway ballastless track arching based on unsupervised learning framework
title_sort Diagnosis of high‐speed railway ballastless track arching based on unsupervised learning framework
author_id_str_mv 92bf566c65343cb3ee04ad963eacf31b
author_id_fullname_str_mv 92bf566c65343cb3ee04ad963eacf31b_***_Yue Hou
author Yue Hou
author2 Xueyang Tang
Yi Wang
Xiaopei Cai
Fei Yang
Yue Hou
format Journal article
container_title Computer‐Aided Civil and Infrastructure Engineering
publishDate 2024
institution Swansea University
issn 1093-9687
1467-8667
doi_str_mv 10.1111/mice.13342
publisher Wiley
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 Vehicle‐mounted detection methods have been widely applied in the maintenance of high‐speed railways (HSRs), providing feasibility for diagnosing ballastless track arching. However, applying detection data faces several key limitations: (1) The threshold mostly requires manual setting, making recognition accuracy highly subjective; (2) the extensive workload of manual inspections makes it challenging to label detection data, hindering the application of supervised learning approaches. To address these problems, this paper utilizes the longitudinal level irregularity data obtained from vehicle‐mounted detection, employing the concept of unsupervised learning for dimensionality reduction, combined with clustering algorithms and minimal label fine‐tuning, to design two frameworks: the fully unsupervised framework (FUF) and the few‐shot fine‐tuned framework (FFF). Experiments on dynamic detection data from a Chinese HSR line were conducted, comparing the performance of data dimensionality reduction, clustering, and classification under different strategy combinations. The results show that the improved variational autoencoder significantly enhances the performance of the encoder in dimensionality reduction, facilitating better feature extraction; the FUF achieves effective clustering outcomes without any labeled samples and its adjusted rand index score exceeded 0.8, showcasing its robustness and applicability in scenarios with no prior annotations; the FFF requires only a small number of labeled samples (labeling ratio of 5%) and achieves excellent performance, with metrics such as accuracy exceeding 0.85, thus greatly reducing the reliance on labeled data. This study offers a novel method for solving engineering issues with limited labeled data, providing an efficient solution for identifying track arching defects and advancing railway infrastructure monitoring.
published_date 2024-09-18T12:50:33Z
_version_ 1810625077466628096
score 11.028798

Similar Items