[en] 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.
Research Center/Unit :
ANAST (Construction Navale, Fluviale et Maritime, Analyse des Systèmes de Transport)
Disciplines :
Civil engineering
Author, co-author :
Morato Dominguez, Pablo Gabriel ; Université de Liège - ULiège > Département ArGEnCo > ANAST (Systèmes de transport et constructions navales)
Nielsen, Jannie S.; University of Aalborg, Denmark > Reliability and Risk Analysis Research Group
Mai, Anh Quang ; Université de Liège - ULiège > Département ArGEnCo > Constructions hydrauliques et navales
Rigo, Philippe ; Université de Liège - ULiège > Département ArGEnCo > Constructions hydrauliques et navales
Language :
English
Title :
POMDP based Maintenance Optimization of Offshore Wind Substructures including Monitoring
Publication date :
27 May 2019
Event name :
13th International Conference on Applications of Statistics and Probability in Civil Engineering (ICASP13)
Event organizer :
University of Seoul
Event place :
Seoul, South Korea
Event date :
from 26-05-2019 to 30-05-2019
Audience :
International
Main work title :
Proceedings of the 13th International Conference on Applications of Statistics and Probability in Civil Engineering (ICASP13)
