View in EDS

Condition Modeling of Railway Drainage Pipes.

Saved in:
Bibliographic Details
Title: Condition Modeling of Railway Drainage Pipes.
Authors: Aljafari, Nour1 (AUTHOR) N.Aljafari@pgr.bham.ac.uk, Burrow, Michael2 (AUTHOR) M.P.Burrow@bham.ac.uk, Ghataora, Gurmel3 (AUTHOR) G.S.Ghataora@bham.ac.uk, Torbaghan, Mehran Eskandari4 (AUTHOR) M.Eskandaritorbaghan@bham.ac.uk, Raja, Jamil5 (AUTHOR) Jamil.Raja@networkrail.co.uk
Source: Journal of Infrastructure Systems. Dec2022, Vol. 28 Issue 4, p1-21. 21p.
Subjects: Network Rail Ltd., Drainage pipes, Railroads, Decision trees, Prediction models, Time management
Abstract: Condition of drainage asset systems can have substantial impact on the structural and operational integrity of railway tracks. It is therefore important to ensure that the various components of the drainage system are well-maintained. To this end, decision makers in the railway industry have been moving toward predictive, risk-informed drainage asset management. The approach aims to optimize the allocation of the limited time and financial resources for maintenance works. To achieve this more research is required to develop predictive condition models for railway drainage assets. This paper describes the development of data-driven condition prediction models using drainage pipe asset records. The models were tested for both structural and service condition prediction. Nine input factors were considered in the prediction models. Significance of the factors was evaluated using connection weight analysis. Four machine learning (ML) algorithms, namely neural networks, decision trees, bagged trees, and k -nearest neighbor, were compared based on their condition prediction performance for pipe drainage assets. The models were developed and tested using field data collected from the UK owner of rail assets, Network Rail. The results demonstrated that bagged trees performed best on a balanced data set with 87% overall accuracy for structural condition prediction and 72% accuracy for service condition prediction. It was found that pipe length, previous condition, years since previous condition, and maintenance were the most significant factors in predicting condition. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Infrastructure Systems is the property of American Society of Civil Engineers and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 159683721
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Condition Modeling of Railway Drainage Pipes.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Aljafari%2C+Nour%22">Aljafari, Nour</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> N.Aljafari@pgr.bham.ac.uk</i><br /><searchLink fieldCode="AR" term="%22Burrow%2C+Michael%22">Burrow, Michael</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> M.P.Burrow@bham.ac.uk</i><br /><searchLink fieldCode="AR" term="%22Ghataora%2C+Gurmel%22">Ghataora, Gurmel</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> G.S.Ghataora@bham.ac.uk</i><br /><searchLink fieldCode="AR" term="%22Torbaghan%2C+Mehran+Eskandari%22">Torbaghan, Mehran Eskandari</searchLink><relatesTo>4</relatesTo> (AUTHOR)<i> M.Eskandaritorbaghan@bham.ac.uk</i><br /><searchLink fieldCode="AR" term="%22Raja%2C+Jamil%22">Raja, Jamil</searchLink><relatesTo>5</relatesTo> (AUTHOR)<i> Jamil.Raja@networkrail.co.uk</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Infrastructure+Systems%22">Journal of Infrastructure Systems</searchLink>. Dec2022, Vol. 28 Issue 4, p1-21. 21p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Network+Rail+Ltd%2E%22">Network Rail Ltd.</searchLink><br /><searchLink fieldCode="DE" term="%22Drainage+pipes%22">Drainage pipes</searchLink><br /><searchLink fieldCode="DE" term="%22Railroads%22">Railroads</searchLink><br /><searchLink fieldCode="DE" term="%22Decision+trees%22">Decision trees</searchLink><br /><searchLink fieldCode="DE" term="%22Prediction+models%22">Prediction models</searchLink><br /><searchLink fieldCode="DE" term="%22Time+management%22">Time management</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Condition of drainage asset systems can have substantial impact on the structural and operational integrity of railway tracks. It is therefore important to ensure that the various components of the drainage system are well-maintained. To this end, decision makers in the railway industry have been moving toward predictive, risk-informed drainage asset management. The approach aims to optimize the allocation of the limited time and financial resources for maintenance works. To achieve this more research is required to develop predictive condition models for railway drainage assets. This paper describes the development of data-driven condition prediction models using drainage pipe asset records. The models were tested for both structural and service condition prediction. Nine input factors were considered in the prediction models. Significance of the factors was evaluated using connection weight analysis. Four machine learning (ML) algorithms, namely neural networks, decision trees, bagged trees, and k -nearest neighbor, were compared based on their condition prediction performance for pipe drainage assets. The models were developed and tested using field data collected from the UK owner of rail assets, Network Rail. The results demonstrated that bagged trees performed best on a balanced data set with 87% overall accuracy for structural condition prediction and 72% accuracy for service condition prediction. It was found that pipe length, previous condition, years since previous condition, and maintenance were the most significant factors in predicting condition. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Infrastructure Systems is the property of American Society of Civil Engineers and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=159683721
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1061/(ASCE)IS.1943-555X.0000708
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 21
        StartPage: 1
    Subjects:
      – SubjectFull: Network Rail Ltd.
        Type: general
      – SubjectFull: Drainage pipes
        Type: general
      – SubjectFull: Railroads
        Type: general
      – SubjectFull: Decision trees
        Type: general
      – SubjectFull: Prediction models
        Type: general
      – SubjectFull: Time management
        Type: general
    Titles:
      – TitleFull: Condition Modeling of Railway Drainage Pipes.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Aljafari, Nour
      – PersonEntity:
          Name:
            NameFull: Burrow, Michael
      – PersonEntity:
          Name:
            NameFull: Ghataora, Gurmel
      – PersonEntity:
          Name:
            NameFull: Torbaghan, Mehran Eskandari
      – PersonEntity:
          Name:
            NameFull: Raja, Jamil
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 12
              Text: Dec2022
              Type: published
              Y: 2022
          Identifiers:
            – Type: issn-print
              Value: 10760342
          Numbering:
            – Type: volume
              Value: 28
            – Type: issue
              Value: 4
          Titles:
            – TitleFull: Journal of Infrastructure Systems
              Type: main
ResultId 1