A POMDP framework for integrated scheduling of infrastructure maintenance and inspection

Kim, Jong Woo; Choi, Go Bong; Lee, Jong Min

doi:10.1016/j.compchemeng.2018.02.015

Cited by 10 publications

(10 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A wide range of O&M processes can be modeled as a Markov process in continuous time, by selecting an appropriate set of state variables (e.g., these variables describe the complex evolution of damage patterns in structural systems) . This process can be converted into an approximate POMDP, by discretizing the time and domain of possible states and by defining costs, available actions, and corresponding transitions . In turn, the POMDP can be solved by implementing an appropriate numerical scheme to identify the optimal control policy.…”

Section: Continuous and Discrete Modeling Of The Maintenance Processmentioning

confidence: 99%

“…If such assumption does not hold true, one needs to define another, more fundamental state, affecting the transitions. That more complex formulation induces a higher computational cost …”

Section: Continuous and Discrete Modeling Of The Maintenance Processmentioning

confidence: 99%

“…[17][18][19] This process can be converted into an approximate POMDP, by discretizing the time and domain of possible states and by defining costs, available actions, and corresponding transitions. 14,20 In turn, the POMDP can be solved by implementing an appropriate numerical scheme to identify the optimal control policy. However, the computational complexity of this optimization depends strongly on the dimensions of the discrete process, 21,22 that in turn depends on the complexity of the original problem and the required quality of the approximation.…”

Section: Problem Statementmentioning

confidence: 99%

“…Applications of VoI analysis to Structural Health Monitoring are presented by Pozzi and Der Kiurehian, Straub, Schweckendiek and Vrouwenvelder, Qin et al, and Zonta et al Evaluation of VoI in sequential infrastructure management is illustrated by Srinivasan and Parlikad . The recent interest in evaluating the economic impact of integrating sensors in infrastructure management is testified by many researches . Assessing the VoI allows for an appropriate calibration of investments in inspections, sensors, and monitoring systems, as the overall investment for collecting information should not exceed its value, In addition, it allows for comparing expensive explorative actions (as installing monitoring systems) with “exploitative” actions (i.e., actions that change the actual condition of the system, as retrofitting a component) on an equal ground.…”

Section: Introductionmentioning

confidence: 99%

“…9 The recent interest in evaluating the economic impact of integrating sensors in infrastructure management is testified by many researches. [10][11][12][13][14] Assessing the VoI allows for an appropriate calibration of investments in inspections, sensors, and monitoring systems, as the overall investment for collecting information should not exceed its value, In addition, it allows for comparing expensive explorative actions (as installing monitoring systems) with "exploitative" actions (i.e., actions that change the actual condition of the system, as retrofitting a component) on an equal ground.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

What makes long‐term monitoring convenient? A parametric analysis of value of information in infrastructure maintenance

Pozzi

2019

Struct Control Health Monit

View full text Add to dashboard Cite

Summary Information collected by monitoring systems can provide a significant economic benefit to the operation and maintenance of infrastructure components only under specific conditions. The information has to be precise, not redundant, related to relevant decision problems under uncertainty as, for example, the appropriate scheduling of maintenance actions, and the decision maker needs to be able to process that information and react timely. All these considerations can be naturally embedded in the value of information (VoI), a utility‐based metric for assessing the impact of the additional information in decision making under uncertainty. In this paper, we investigate the relation between the VoI and key features of the monitoring system, of the component deterioration and of the decision‐making process, including measure accuracy and availability, deterioration rates, damage predictability, reaction time, maintenance costs, and the economic discount factor. By leveraging previous work, we model the maintenance process as a partially observable Markov decision process, and we compute the VoI of long‐term monitoring. Our proposed framework allows for a detailed quantitative analysis on the joint effects of these features and can be useful to identify conditions when the benefit of monitoring is high, to assign priorities among components that deserve to be instrumented or to optimize the allocation of resources to monitoring efforts.

show abstract

Section: Continuous and Discrete Modeling Of The Maintenance Processmentioning

confidence: 99%

“…If such assumption does not hold true, one needs to define another, more fundamental state, affecting the transitions. That more complex formulation induces a higher computational cost …”

Section: Continuous and Discrete Modeling Of The Maintenance Processmentioning

confidence: 99%