Sewer Inspection Prioritization Using a Defect-Based Bayesian Belief Network Model

Mohamed Elmasry, Zayed Tarek Zayed, Alaa Hawari

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

5 Citations (Scopus)

Abstract

In order to successfully implement an asset management program, an accurate and reliable deterioration model for assets should be available. Deterioration models are considered as the basis for predicting and prioritizing future maintenance, rehabilitation, or replacement activities of assets. Sewer agencies are seeking different methods to prioritize inspection of sewer pipes in presence of financial constraints and deteriorating pipelines. This paper presents the development of a defect based deterioration model using Bayesian belief network (BBN) in sewer pipelines to be used in inspection prioritization. Different types of defects found in an existing sewage network were collected from closed circuit television (CCTV) inspection reports and used in creating the model to determine the likelihood of a sewage pipeline to be in a certain condition state. The BBN is used to generate dependency between different defects and their effect on the overall condition of the pipe. Monte-Carlo simulation (MCS) was introduced to eliminate the uncertainties that could arise in the model due to independent events that would be propagated through the BBN to assess the final dependent posterior probabilities. BBN is considered as an efficient tool because it deals with inherent uncertainties and handles complex interdependencies using conditional probabilities. The developed model could be used as a decision support tool by which decision makers could plan inspection of deteriorated sections.

Original languageEnglish
Title of host publicationPipelines 2016
Subtitle of host publicationOut of Sight, Out of Mind, Not Out of Risk - Proceedings of the Pipelines 2016 Conference
EditorsBryon L. Livingston, Jim Geisbush, Cliff Cate, Jeffrey W. Heidrick, Anna Pridmore
PublisherAmerican Society of Civil Engineers (ASCE)
Pages613-625
Number of pages13
ISBN (Electronic)9780784479957
DOIs
Publication statusPublished - 2016
EventPipelines 2016 Conference: Out of Sight, Out of Mind, Not Out of Risk - Kansas City, United States
Duration: 17 Jul 201620 Jul 2016

Publication series

NamePipelines 2016: Out of Sight, Out of Mind, Not Out of Risk - Proceedings of the Pipelines 2016 Conference

Conference

ConferencePipelines 2016 Conference: Out of Sight, Out of Mind, Not Out of Risk
Country/TerritoryUnited States
CityKansas City
Period17/07/1620/07/16

ASJC Scopus subject areas

  • Safety, Risk, Reliability and Quality
  • Mechanical Engineering
  • Civil and Structural Engineering
  • Geotechnical Engineering and Engineering Geology

Fingerprint

Dive into the research topics of 'Sewer Inspection Prioritization Using a Defect-Based Bayesian Belief Network Model'. Together they form a unique fingerprint.

Cite this