YaBeSH Engineering and Technology Library

    • Journals
    • PaperQuest
    • YSE Standards
    • YaBeSH
    • Login
    View Item 
    •   YE&T Library
    • ASCE
    • Journal of Performance of Constructed Facilities
    • View Item
    •   YE&T Library
    • ASCE
    • Journal of Performance of Constructed Facilities
    • View Item
    • All Fields
    • Source Title
    • Year
    • Publisher
    • Title
    • Subject
    • Author
    • DOI
    • ISBN
    Advanced Search
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Archive

    Modeling Pipe Break Data Using Survival Analysis with Machine Learning Imputation Methods

    Source: Journal of Performance of Constructed Facilities:;2021:;Volume ( 035 ):;issue: 005::page 04021071-1
    Author:
    Hao Xu
    ,
    Sunil K. Sinha
    DOI: 10.1061/(ASCE)CF.1943-5509.0001649
    Publisher: ASCE
    Abstract: The development of asset life estimation tools based on historical data is essential to the effective management of pipeline assets. One tool that may assist with asset management is survival analysis. However, left-truncated break records pose a challenge in the practice of survival analysis to obtain sound inferences and predictions. In this study, we propose a data-driven approach that integrates machine learning imputation methods with survival analysis. To demonstrate the proposed methodology, we perform a case study using ductile iron (DI) water distribution pipes from an anonymized utility in the midwestern United States. Two artificial neural network (ANN) models are developed as imputation methods to calibrate the survival curves and mean time to first failure (MTTF) estimates from the Weibull proportional hazards model (WPHM). Results show that the MTTF estimation bias is reduced from 14.3% to 2.1% by using imputation as a preceding procedure. Empirical findings show that despite the limited accuracy of imputation models, the use of imputation methods can still improve the survival analysis results and mitigate the impact of left-truncated break records.
    • Download: (368.8Kb)
    • Show Full MetaData Hide Full MetaData
    • Get RIS
    • Item Order
    • Go To Publisher
    • Price: 5000 Rial
    • Statistics

      Modeling Pipe Break Data Using Survival Analysis with Machine Learning Imputation Methods

    URI
    http://yetl.yabesh.ir/yetl1/handle/yetl/4271935
    Collections
    • Journal of Performance of Constructed Facilities

    Show full item record

    contributor authorHao Xu
    contributor authorSunil K. Sinha
    date accessioned2022-02-01T21:44:13Z
    date available2022-02-01T21:44:13Z
    date issued10/1/2021
    identifier other%28ASCE%29CF.1943-5509.0001649.pdf
    identifier urihttp://yetl.yabesh.ir/yetl1/handle/yetl/4271935
    description abstractThe development of asset life estimation tools based on historical data is essential to the effective management of pipeline assets. One tool that may assist with asset management is survival analysis. However, left-truncated break records pose a challenge in the practice of survival analysis to obtain sound inferences and predictions. In this study, we propose a data-driven approach that integrates machine learning imputation methods with survival analysis. To demonstrate the proposed methodology, we perform a case study using ductile iron (DI) water distribution pipes from an anonymized utility in the midwestern United States. Two artificial neural network (ANN) models are developed as imputation methods to calibrate the survival curves and mean time to first failure (MTTF) estimates from the Weibull proportional hazards model (WPHM). Results show that the MTTF estimation bias is reduced from 14.3% to 2.1% by using imputation as a preceding procedure. Empirical findings show that despite the limited accuracy of imputation models, the use of imputation methods can still improve the survival analysis results and mitigate the impact of left-truncated break records.
    publisherASCE
    titleModeling Pipe Break Data Using Survival Analysis with Machine Learning Imputation Methods
    typeJournal Paper
    journal volume35
    journal issue5
    journal titleJournal of Performance of Constructed Facilities
    identifier doi10.1061/(ASCE)CF.1943-5509.0001649
    journal fristpage04021071-1
    journal lastpage04021071-9
    page9
    treeJournal of Performance of Constructed Facilities:;2021:;Volume ( 035 ):;issue: 005
    contenttypeFulltext
    DSpace software copyright © 2002-2015  DuraSpace
    نرم افزار کتابخانه دیجیتال "دی اسپیس" فارسی شده توسط یابش برای کتابخانه های ایرانی | تماس با یابش
    yabeshDSpacePersian
     
    DSpace software copyright © 2002-2015  DuraSpace
    نرم افزار کتابخانه دیجیتال "دی اسپیس" فارسی شده توسط یابش برای کتابخانه های ایرانی | تماس با یابش
    yabeshDSpacePersian