Convolutional Autoencoder-Based Damage Detection for Urban Railway Tracks Using an Ultra-Weak FBG Array Monitoring System

Urban railway tracks inevitably suffer damage due to the cyclic load of trains, necessitating structural health monitoring (SHM) with the primary purpose of damage detection. Recently, the ultra-weak fiber Bragg grating (UWFBG) monitoring system has been employed for long-term monitoring of urban ra...

Full description

Saved in:
Bibliographic Details
Published in:IEEE sensors journal Vol. 24; no. 20; pp. 33585 - 33593
Main Authors: Chen, Jiahui, Li, Qiuyi, Zhang, Shijie, Lin, Chao, Wei, Shiyin
Format: Journal Article
Language:English
Published: New York IEEE 15.10.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Artificial neural networks
Autocorrelation functions
Bragg gratings
Cyclic loads
Damage detection
Data mining
Data models
deep convolutional autoencoder (DCAE)
Error detection
Feature extraction
Machine learning
Monitoring
Monitoring systems
Optical fibers
Rail transportation
Railway engineering
Railway tracks
Reconstruction
Sensors
Structural health monitoring
Trains
ultra-weak fiber Bragg grating (UWFBG)
Unsupervised learning
urban railway track
vibration monitoring
Vibrations
ISSN:1530-437X, 1558-1748
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Urban railway tracks inevitably suffer damage due to the cyclic load of trains, necessitating structural health monitoring (SHM) with the primary purpose of damage detection. Recently, the ultra-weak fiber Bragg grating (UWFBG) monitoring system has been employed for long-term monitoring of urban railway tracks due to its ability to multiplex thousands of sensors on a single optical fiber. The vast amount of data collected imposes the importance of data-driven damage detection methods. Given the lack of labeled damage datasets, unsupervised learning methods are highlighted. This study proposes a damage detection method for urban railway tracks based on an unsupervised deep neural network, referred to as deep convolutional autoencoder (DCAE). The monitored data are first processed to the autocorrelation functions (ACFs) to be aligned across different channels, and then, the multichannel ACFs are used as the inputs of the DCAE model. Finally, the reconstruction error of the DCAE model is employed as the damage index, and field monitoring data are utilized to verify the proposed method. The results show that the proposed damage index is sensitive to track damage, and the precision of damage detection increases with the threshold of reconstruction error, reaching a peak at 1. The method also achieves a maximum F1 score of 0.90.
AbstractList Urban railway tracks inevitably suffer damage due to the cyclic load of trains, necessitating structural health monitoring (SHM) with the primary purpose of damage detection. Recently, the ultra-weak fiber Bragg grating (UWFBG) monitoring system has been employed for long-term monitoring of urban railway tracks due to its ability to multiplex thousands of sensors on a single optical fiber. The vast amount of data collected imposes the importance of data-driven damage detection methods. Given the lack of labeled damage datasets, unsupervised learning methods are highlighted. This study proposes a damage detection method for urban railway tracks based on an unsupervised deep neural network, referred to as deep convolutional autoencoder (DCAE). The monitored data are first processed to the autocorrelation functions (ACFs) to be aligned across different channels, and then, the multichannel ACFs are used as the inputs of the DCAE model. Finally, the reconstruction error of the DCAE model is employed as the damage index, and field monitoring data are utilized to verify the proposed method. The results show that the proposed damage index is sensitive to track damage, and the precision of damage detection increases with the threshold of reconstruction error, reaching a peak at 1. The method also achieves a maximum F1 score of 0.90.
Author Zhang, Shijie
Lin, Chao
Chen, Jiahui
Li, Qiuyi
Wei, Shiyin
Author_xml – sequence: 1
  givenname: Jiahui
  surname: Chen
  fullname: Chen, Jiahui
  email: chenjh7977@126.com
  organization: China Railway Siyuan Survey and Design Group Company Ltd., Wuhan, China
– sequence: 2
  givenname: Qiuyi
  surname: Li
  fullname: Li, Qiuyi
  email: 003713@crfsdi.com
  organization: China Railway Siyuan Survey and Design Group Company Ltd., Wuhan, China
– sequence: 3
  givenname: Shijie
  surname: Zhang
  fullname: Zhang, Shijie
  email: 004193@crfsdi.com
  organization: China Railway Siyuan Survey and Design Group Company Ltd., Wuhan, China
– sequence: 4
  givenname: Chao
  surname: Lin
  fullname: Lin, Chao
  email: 005672@crfsdi.com
  organization: China Railway Siyuan Survey and Design Group Company Ltd., Wuhan, China
– sequence: 5
  givenname: Shiyin
  orcidid: 0000-0001-6204-7128
  surname: Wei
  fullname: Wei, Shiyin
  email: shiyin.wei@hit.edu.cn
  organization: School of Civil Engineering, Harbin Institute of Technology, Harbin, China
BookMark eNp9kU9LAzEQxYMo2FY_gOAh4HlrstlNdo_9r1IVbIveljSdLdtuNzXJKv32ZmkP4sG5zDD83sB700bnla4AoRtKupSS9P5pNnrphiSMuiyilMfhGWrROE4CKqLkvJkZCSImPi5R29oNITQVsWihw0BXX7qsXaErWeJe7TRUSq_ABH1pYYWHcifXgIfgQDUQzrXBC7OUFX6TRfktD3hupNpavLBFtcZ-vyidkcE7yC0e9ye4Z4yHnnVVOG0aZHawDnZX6CKXpYXrU--gxXg0HzwE09fJ46A3DRTj3AV0GaU8ZcCSlYQ0YSnngnDhKwKRi1SJhOdxKIVSHiRLHoVULWOSqjxnkgrWQXfHu3ujP2uwLtvo2nizNmOUCsriJGKeEkdKGW2tgTxThZONYe-lKDNKsibnrMk5a3LOTjl7Jf2j3JtiJ83hX83tUVMAwC_eP0wIwn4Ak5GKzg
CODEN ISJEAZ
CitedBy_id crossref_primary_10_1111_mice_13342
crossref_primary_10_1109_JSEN_2025_3574559
Cites_doi 10.1007/s11071-023-08391-0
10.1177/1475921720972416
10.1177/1475921710365437
10.1016/j.engstruct.2021.113064
10.3390/buildings14051239
10.1007/s00366-017-0563-5
10.1177/1475921720942836
10.1016/j.ymssp.2022.109175
10.1016/j.eng.2018.11.027
10.1016/j.engstruct.2008.05.024
10.1016/j.engstruct.2021.113783
10.3390/su15065391
10.1016/j.engstruct.2018.05.109
10.1016/j.engstruct.2016.04.057
10.1016/S0263-8223(03)00023-0
10.1016/j.jsv.2007.12.008
10.1177/1475921720926267
10.1016/j.jsv.2007.01.021
10.1007/s00366-021-01584-4
10.1016/j.jprocont.2024.103176
10.3390/app7050510
10.3390/app11062610
10.3390/s21103333
10.1016/j.ymssp.2012.02.014
10.1177/14759217221104224
10.1016/j.apacoust.2019.107133
10.1177/14759217211069842
10.1002/stc.1886
10.3390/s20102778
10.1016/j.jsv.2011.09.004
10.1016/j.ymssp.2022.109287
10.1016/j.ymssp.2020.107077
10.1002/stc.1503
10.3390/s22051839
10.1177/1475921716639587
10.1016/j.measurement.2018.10.095
10.1177/1475921718804132
10.1177/1475921720921772
10.1177/1475921720934051
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID 97E
RIA
RIE
AAYXX
CITATION
7SP
7U5
8FD
L7M
DOI 10.1109/JSEN.2024.3411652
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Electronics & Communications Abstracts
Solid State and Superconductivity Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Solid State and Superconductivity Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList Solid State and Superconductivity Abstracts
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL) (UW System Shared)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Geography
Engineering
EISSN 1558-1748
EndPage 33593
ExternalDocumentID 10_1109_JSEN_2024_3411652
10558770
Genre orig-research
GrantInformation_xml – fundername: China Postdoctoral Science Foundation
  grantid: 2023M744101
  funderid: 10.13039/501100002858
– fundername: National Natural Science Foundation of China
  grantid: 52208311
– fundername: Funding for the Postdoctoral Innovative Practice Position in Hubei Province for the 2022–2023 year
– fundername: Key Research Project of China Railway Siyuan Survey and Design Group Company Ltd.
  grantid: KY2023001S
– fundername: National Natural Science Foundation of China
  grantid: 52208311; U23A20660
– fundername: Major Scientific and Technological Research and Development projects of China Railway Construction Company Ltd.
  grantid: 2021-A03
– fundername: Young Elite Scientists Sponsorship Program by China Association for Science and Technology (CAST)
  grantid: 2021QNRC001
GroupedDBID -~X
0R~
29I
4.4
5GY
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
AENEX
AGQYO
AHBIQ
AJQPL
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
EBS
F5P
HZ~
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
TWZ
AAYXX
CITATION
7SP
7U5
8FD
L7M
ID FETCH-LOGICAL-c366t-1b49693e38dae98396670677774e7f79c786f52a7cc4960b6421cb509cff3a173
IEDL.DBID RIE
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001338604800172&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1530-437X
IngestDate Mon Jun 30 10:19:11 EDT 2025
Tue Nov 18 22:37:17 EST 2025
Sat Nov 29 06:40:05 EST 2025
Wed Aug 27 02:15:49 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 20
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c366t-1b49693e38dae98396670677774e7f79c786f52a7cc4960b6421cb509cff3a173
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0001-6204-7128
PQID 3117135843
PQPubID 75733
PageCount 9
ParticipantIDs crossref_citationtrail_10_1109_JSEN_2024_3411652
proquest_journals_3117135843
crossref_primary_10_1109_JSEN_2024_3411652
ieee_primary_10558770
PublicationCentury 2000
PublicationDate 2024-10-15
PublicationDateYYYYMMDD 2024-10-15
PublicationDate_xml – month: 10
  year: 2024
  text: 2024-10-15
  day: 15
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE sensors journal
PublicationTitleAbbrev JSEN
PublicationYear 2024
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref35
ref12
ref34
ref15
ref37
ref14
ref36
ref31
ref30
ref11
ref33
ref10
ref32
ref2
ref1
ref17
ref16
ref38
ref19
ref18
ref24
ref23
ref26
ref25
ref20
ref22
ref21
ref28
ref27
ref29
ref8
ref7
ref9
ref4
ref3
ref6
ref5
ref40
Zong (ref39)
References_xml – ident: ref7
  doi: 10.1007/s11071-023-08391-0
– ident: ref3
  doi: 10.1177/1475921720972416
– ident: ref32
  doi: 10.1177/1475921710365437
– ident: ref20
  doi: 10.1016/j.engstruct.2021.113064
– ident: ref36
  doi: 10.3390/buildings14051239
– ident: ref9
  doi: 10.1007/s00366-017-0563-5
– ident: ref30
  doi: 10.1177/1475921720942836
– ident: ref5
  doi: 10.1016/j.ymssp.2022.109175
– ident: ref2
  doi: 10.1016/j.eng.2018.11.027
– ident: ref10
  doi: 10.1016/j.engstruct.2008.05.024
– ident: ref24
  doi: 10.1016/j.engstruct.2021.113783
– ident: ref1
  doi: 10.3390/su15065391
– ident: ref27
  doi: 10.1016/j.engstruct.2018.05.109
– ident: ref8
  doi: 10.1016/j.engstruct.2016.04.057
– ident: ref16
  doi: 10.1016/S0263-8223(03)00023-0
– ident: ref15
  doi: 10.1016/j.jsv.2007.12.008
– ident: ref21
  doi: 10.1177/1475921720926267
– ident: ref11
  doi: 10.1016/j.jsv.2007.01.021
– ident: ref25
  doi: 10.1007/s00366-021-01584-4
– ident: ref38
  doi: 10.1016/j.jprocont.2024.103176
– ident: ref6
  doi: 10.3390/app7050510
– ident: ref29
  doi: 10.3390/app11062610
– ident: ref28
  doi: 10.3390/s21103333
– ident: ref14
  doi: 10.1016/j.ymssp.2012.02.014
– ident: ref19
  doi: 10.1177/14759217221104224
– ident: ref34
  doi: 10.1016/j.apacoust.2019.107133
– ident: ref26
  doi: 10.1177/14759217211069842
– ident: ref17
  doi: 10.1002/stc.1886
– ident: ref22
  doi: 10.3390/s20102778
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Represent.
  ident: ref39
  article-title: Deep autoencoding Gaussian mixture model for unsupervised anomaly detection
– ident: ref12
  doi: 10.1016/j.jsv.2011.09.004
– ident: ref35
  doi: 10.1016/j.ymssp.2022.109287
– ident: ref4
  doi: 10.1016/j.ymssp.2020.107077
– ident: ref13
  doi: 10.1002/stc.1503
– ident: ref31
  doi: 10.3390/s22051839
– ident: ref18
  doi: 10.1177/1475921716639587
– ident: ref37
  doi: 10.1016/j.measurement.2018.10.095
– ident: ref23
  doi: 10.1177/1475921718804132
– ident: ref33
  doi: 10.1177/1475921720921772
– ident: ref40
  doi: 10.1177/1475921720934051
SSID ssj0019757
Score 2.429043
Snippet Urban railway tracks inevitably suffer damage due to the cyclic load of trains, necessitating structural health monitoring (SHM) with the primary purpose of...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 33585
SubjectTerms Artificial neural networks
Autocorrelation functions
Bragg gratings
Cyclic loads
Damage detection
Data mining
Data models
deep convolutional autoencoder (DCAE)
Error detection
Feature extraction
Machine learning
Monitoring
Monitoring systems
Optical fibers
Rail transportation
Railway engineering
Railway tracks
Reconstruction
Sensors
Structural health monitoring
Trains
ultra-weak fiber Bragg grating (UWFBG)
Unsupervised learning
urban railway track
vibration monitoring
Vibrations
Title Convolutional Autoencoder-Based Damage Detection for Urban Railway Tracks Using an Ultra-Weak FBG Array Monitoring System
URI https://ieeexplore.ieee.org/document/10558770
https://www.proquest.com/docview/3117135843
Volume 24
WOSCitedRecordID wos001338604800172&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE/IET Electronic Library (IEL) (UW System Shared)
  customDbUrl:
  eissn: 1558-1748
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0019757
  issn: 1530-437X
  databaseCode: RIE
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dSxwxEA8qgu2DWmvx6gd56JMQ3Wyym82jX6dIOYp67b0tSTah4rlX9vYs99-byUZRpAXflmWyDPyS-djM_Aahby4pdGqZJkqoinDlONHG72Wd8cpVmVMm8HT__C4Gg2I0kj9is3rohbHWhuIzewCP4S6_mpgZ_Co7hGGOhRA-Q18UQnTNWs9XBlIEWk9_ghPCmRjFK0yayMPL67OBTwVTfuBtNs2z9JUTClNV3pji4F_6a-_UbB2txkASH3XIf0ILtt5AH1_QC26glTjh_Pf8M5qfTOqHuM1g2aydAIVlZRty7B1ZhU_VvTct-NS2oTirxj6axcNGqxpfqdvxXzXH3q-ZuykOVQbYvx-O20aRX1bd4f7xuVel8UKdkQAFcMeGvomG_bObkwsSxy4Qw_K8JVRzmUtmWVEpK30AlecCeOZ8oGiFE9KIIndZqoQxXjDR0CprtA88jHNMUcG-oKV6UtsthLNEszRTHMIErgqrmHTApZRTCpwEVQ8lTziUJnKSw2iMcRlyk0SWAF0J0JURuh7af17ypyPk-J_wJmD1QrCDqYd2ntAu45mdloxSmFdYcPb1H8u20Qf4Orgumu2gpbaZ2V20bB7a22mzF7bjI1Xy3KQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwELYqWgl66INSdQsUH3qqZIhjJ46PvBZKt6sK2HZvke3YKmLJomyWav99PY5BINRK3KJorIz02fOIZ75B6LNLCp1apokSqiJcOU608XtZZ7xyVeaUCTzdPwdiOCzGY_kjNquHXhhrbSg-s9vwGO7yq6mZw6-yHRjmWAjhM_TnGecp7dq17i4NpAjEnv4MJ4QzMY6XmDSROydnh0OfDKZ821ttmmfpAzcU5qo8MsbBw_RfP1G3N-hVDCXxbof9W_TM1qvo5T2CwVW0HGec_168Q4v9aX0TNxosm7dTILGsbEP2vCur8IG68sYFH9g2lGfV2MezeNRoVeNTdTH5oxbYezZzOcOhzgD796NJ2yjyy6pL3N878qo0XqgzE6AA7vjQ19Cof3i-f0zi4AViWJ63hGouc8ksKyplpQ-h8lwA05wPFa1wQhpR5C5LlTDGCyYammWN9qGHcY4pKth7tFRPa_sB4SzRLM0Uh0CBq8IqJh2wKeWUAitB1UPJLQ6liazkMBxjUobsJJElQFcCdGWEroe-3C257ig5_ie8BljdE-xg6qGNW7TLeGpnJaMUJhYWnH38x7IttHx8_n1QDr4Ov62jFfgSODKabaCltpnbTfTC3LQXs-ZT2Jp_Afj-3-s
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Convolutional+Autoencoder-Based+Damage+Detection+for+Urban+Railway+Tracks+Using+an+Ultra-Weak+FBG+Array+Monitoring+System&rft.jtitle=IEEE+sensors+journal&rft.au=Chen%2C+Jiahui&rft.au=Li%2C+Qiuyi&rft.au=Zhang%2C+Shijie&rft.au=Lin%2C+Chao&rft.date=2024-10-15&rft.issn=1530-437X&rft.eissn=1558-1748&rft.volume=24&rft.issue=20&rft.spage=33585&rft.epage=33593&rft_id=info:doi/10.1109%2FJSEN.2024.3411652&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JSEN_2024_3411652
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1530-437X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1530-437X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1530-437X&client=summon