Computational framework for risk-based planning of inspections, maintenance, and condition monitoring using discrete Bayesian networks

Bidragets oversatte titel: Computational framework for risk-based planning of inspections, maintenance, and condition monitoring using discrete Bayesian networks

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

6 Citationer (Scopus)
141 Downloads (Pure)

Resumé

This paper presents a computational framework for risk-based planning of inspections and repairs for deteriorating components. Two distinct types of decision rules are used to model decisions: simple decision rules that depend on constants or observed variables (e.g. inspection outcome), and advanced decision rules that depend on variables found using Bayesian updating (e.g. probability of failure). Two decision models are developed, both relying on dynamic Bayesian networks (dBNs) for deterioration modelling. For simple decision rules, dBNs are used directly for exact assessment of total expected life-cycle costs. For advanced decision rules, simulations are performed to estimate the expected costs, and dBNs are used within the simulations for decision-making. Information from inspections and condition monitoring are included if available. An example in the paper demonstrates the framework and the implemented strategies and decision rules, including various types of condition-based maintenance. The strategies using advanced decision rules lead to reduced costs compared to the simple decision rules when condition monitoring is applied, and the value of condition monitoring is estimated by comparing the lowest costs obtained with and without condition monitoring.

OriginalsprogEngelsk
TidsskriftStructure & Infrastructure Engineering
Vol/bind14
Udgave nummer8
Sider (fra-til)1082-1094
Antal sider13
ISSN1573-2479
DOI
StatusUdgivet - 3 aug. 2018

Fingerprint

Condition monitoring
Bayesian networks
Inspection
Planning
monitoring
Costs
Deterioration
Life cycle
Repair
cost
Decision making
decision
inspection
planning
repair
simulation
life cycle
decision making

Emneord

  • Maintenance & inspection
  • Risk & probability analysis
  • Decision support systems
  • Monitoring
  • Reliability
  • Bayesian networks

Citer dette

@article{1d0adfaaa76a4a8eb6625abccfe54102,
title = "Computational framework for risk-based planning of inspections, maintenance, and condition monitoring using discrete Bayesian networks",
abstract = "This paper presents a computational framework for risk-based planning of inspections and repairs for deteriorating components. Two distinct types of decision rules are used to model decisions: simple decision rules that depend on constants or observed variables (e.g. inspection outcome), and advanced decision rules that depend on variables found using Bayesian updating (e.g. probability of failure). Two decision models are developed, both relying on dynamic Bayesian networks (dBNs) for deterioration modelling. For simple decision rules, dBNs are used directly for exact assessment of total expected life-cycle costs. For advanced decision rules, simulations are performed to estimate the expected costs, and dBNs are used within the simulations for decision-making. Information from inspections and condition monitoring are included if available. An example in the paper demonstrates the framework and the implemented strategies and decision rules, including various types of condition-based maintenance. The strategies using advanced decision rules lead to reduced costs compared to the simple decision rules when condition monitoring is applied, and the value of condition monitoring is estimated by comparing the lowest costs obtained with and without condition monitoring.",
keywords = "Maintenance & inspection, Risk & probability analysis, Decision support systems, Monitoring, Reliability, Bayesian networks, reliability, risk & probability analysis, monitoring, decision support systems, Maintenance & inspection, Risk & probability analysis, Decision support systems, Monitoring, Reliability, Bayesian networks",
author = "Nielsen, {Jannie S{\o}nderk{\ae}r} and S{\o}rensen, {John Dalsgaard}",
year = "2018",
month = "8",
day = "3",
doi = "10.1080/15732479.2017.1387155",
language = "English",
volume = "14",
pages = "1082--1094",
journal = "Structure & Infrastructure Engineering",
issn = "1573-2479",
publisher = "Taylor & Francis",
number = "8",

}

TY - JOUR

T1 - Computational framework for risk-based planning of inspections, maintenance, and condition monitoring using discrete Bayesian networks

AU - Nielsen, Jannie Sønderkær

AU - Sørensen, John Dalsgaard

PY - 2018/8/3

Y1 - 2018/8/3

N2 - This paper presents a computational framework for risk-based planning of inspections and repairs for deteriorating components. Two distinct types of decision rules are used to model decisions: simple decision rules that depend on constants or observed variables (e.g. inspection outcome), and advanced decision rules that depend on variables found using Bayesian updating (e.g. probability of failure). Two decision models are developed, both relying on dynamic Bayesian networks (dBNs) for deterioration modelling. For simple decision rules, dBNs are used directly for exact assessment of total expected life-cycle costs. For advanced decision rules, simulations are performed to estimate the expected costs, and dBNs are used within the simulations for decision-making. Information from inspections and condition monitoring are included if available. An example in the paper demonstrates the framework and the implemented strategies and decision rules, including various types of condition-based maintenance. The strategies using advanced decision rules lead to reduced costs compared to the simple decision rules when condition monitoring is applied, and the value of condition monitoring is estimated by comparing the lowest costs obtained with and without condition monitoring.

AB - This paper presents a computational framework for risk-based planning of inspections and repairs for deteriorating components. Two distinct types of decision rules are used to model decisions: simple decision rules that depend on constants or observed variables (e.g. inspection outcome), and advanced decision rules that depend on variables found using Bayesian updating (e.g. probability of failure). Two decision models are developed, both relying on dynamic Bayesian networks (dBNs) for deterioration modelling. For simple decision rules, dBNs are used directly for exact assessment of total expected life-cycle costs. For advanced decision rules, simulations are performed to estimate the expected costs, and dBNs are used within the simulations for decision-making. Information from inspections and condition monitoring are included if available. An example in the paper demonstrates the framework and the implemented strategies and decision rules, including various types of condition-based maintenance. The strategies using advanced decision rules lead to reduced costs compared to the simple decision rules when condition monitoring is applied, and the value of condition monitoring is estimated by comparing the lowest costs obtained with and without condition monitoring.

KW - Maintenance & inspection

KW - Risk & probability analysis

KW - Decision support systems

KW - Monitoring

KW - Reliability

KW - Bayesian networks

KW - reliability

KW - risk & probability analysis

KW - monitoring

KW - decision support systems

KW - Maintenance & inspection

KW - Risk & probability analysis

KW - Decision support systems

KW - Monitoring

KW - Reliability

KW - Bayesian networks

UR - http://www.scopus.com/inward/record.url?scp=85031412303&partnerID=8YFLogxK

U2 - 10.1080/15732479.2017.1387155

DO - 10.1080/15732479.2017.1387155

M3 - Journal article

VL - 14

SP - 1082

EP - 1094

JO - Structure & Infrastructure Engineering

JF - Structure & Infrastructure Engineering

SN - 1573-2479

IS - 8

ER -