POMDP based Maintenance Optimization of Offshore Wind Substructures including Monitoring

Pablo G. Morato, Jannie Sønderkær Nielsen, Anh Quang Mai, Philippe Rigo

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

Resumé

Sequential decision making under uncertainty is a complex task limited normally by computational requirements. A novel methodology is proposed in this paper to identify the optimal maintenance strategy of a structural component by using a point-based Partially Observable Markov Decision Process (POMDP). The framework integrates a dynamic bayesian network to track the deterioration over time with a POMDP model for the generation of a dynamic policy. The methodology is applied to an example quantifying whether a monitoring scheme is cost effective. This complex decision problem comprised of 200 damage states is solved accurately within 60 seconds of computational time.
OriginalsprogEngelsk
TitelProceedings of the 13th International Conference on Applications of Statistics and Probability in Civil Engineering
StatusAccepteret/In press - 2019
Begivenhed13th International Conference on Applications of Statistics and Probability in Civil Engineering - Seoul National University, Seoul, Sydkorea
Varighed: 26 maj 201930 maj 2019
https://www.icasp13.snu.ac.kr/

Konference

Konference13th International Conference on Applications of Statistics and Probability in Civil Engineering
LokationSeoul National University
LandSydkorea
BySeoul
Periode26/05/201930/05/2019
Internetadresse

Fingerprint

Monitoring
Bayesian networks
Deterioration
Decision making
Costs
Uncertainty

Citer dette

Morato, P. G., Nielsen, J. S., Mai, A. Q., & Rigo, P. (Accepteret/In press). POMDP based Maintenance Optimization of Offshore Wind Substructures including Monitoring. I Proceedings of the 13th International Conference on Applications of Statistics and Probability in Civil Engineering
Morato, Pablo G. ; Nielsen, Jannie Sønderkær ; Mai, Anh Quang ; Rigo, Philippe. / POMDP based Maintenance Optimization of Offshore Wind Substructures including Monitoring. Proceedings of the 13th International Conference on Applications of Statistics and Probability in Civil Engineering. 2019.
@inproceedings{97e26b9e89bd41a9924d7588ff3415c0,
title = "POMDP based Maintenance Optimization of Offshore Wind Substructures including Monitoring",
abstract = "Sequential decision making under uncertainty is a complex task limited normally by computational requirements. A novel methodology is proposed in this paper to identify the optimal maintenance strategy of a structural component by using a point-based Partially Observable Markov Decision Process (POMDP). The framework integrates a dynamic bayesian network to track the deterioration over time with a POMDP model for the generation of a dynamic policy. The methodology is applied to an example quantifying whether a monitoring scheme is cost effective. This complex decision problem comprised of 200 damage states is solved accurately within 60 seconds of computational time.",
author = "Morato, {Pablo G.} and Nielsen, {Jannie S{\o}nderk{\ae}r} and Mai, {Anh Quang} and Philippe Rigo",
year = "2019",
language = "English",
booktitle = "Proceedings of the 13th International Conference on Applications of Statistics and Probability in Civil Engineering",

}

Morato, PG, Nielsen, JS, Mai, AQ & Rigo, P 2019, POMDP based Maintenance Optimization of Offshore Wind Substructures including Monitoring. i Proceedings of the 13th International Conference on Applications of Statistics and Probability in Civil Engineering., Seoul, Sydkorea, 26/05/2019.

POMDP based Maintenance Optimization of Offshore Wind Substructures including Monitoring. / Morato, Pablo G.; Nielsen, Jannie Sønderkær; Mai, Anh Quang; Rigo, Philippe.

Proceedings of the 13th International Conference on Applications of Statistics and Probability in Civil Engineering. 2019.

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - POMDP based Maintenance Optimization of Offshore Wind Substructures including Monitoring

AU - Morato, Pablo G.

AU - Nielsen, Jannie Sønderkær

AU - Mai, Anh Quang

AU - Rigo, Philippe

PY - 2019

Y1 - 2019

N2 - Sequential decision making under uncertainty is a complex task limited normally by computational requirements. A novel methodology is proposed in this paper to identify the optimal maintenance strategy of a structural component by using a point-based Partially Observable Markov Decision Process (POMDP). The framework integrates a dynamic bayesian network to track the deterioration over time with a POMDP model for the generation of a dynamic policy. The methodology is applied to an example quantifying whether a monitoring scheme is cost effective. This complex decision problem comprised of 200 damage states is solved accurately within 60 seconds of computational time.

AB - Sequential decision making under uncertainty is a complex task limited normally by computational requirements. A novel methodology is proposed in this paper to identify the optimal maintenance strategy of a structural component by using a point-based Partially Observable Markov Decision Process (POMDP). The framework integrates a dynamic bayesian network to track the deterioration over time with a POMDP model for the generation of a dynamic policy. The methodology is applied to an example quantifying whether a monitoring scheme is cost effective. This complex decision problem comprised of 200 damage states is solved accurately within 60 seconds of computational time.

M3 - Article in proceeding

BT - Proceedings of the 13th International Conference on Applications of Statistics and Probability in Civil Engineering

ER -

Morato PG, Nielsen JS, Mai AQ, Rigo P. POMDP based Maintenance Optimization of Offshore Wind Substructures including Monitoring. I Proceedings of the 13th International Conference on Applications of Statistics and Probability in Civil Engineering. 2019