Afficher la notice abrégée

A Classification Approach to Efficient Global Optimization in Presence of Non-Computable Domains

hal.structure.identifierInstitut de Recherche de l'Ecole Navale [IRENAV]
dc.contributor.authorSACHER, Matthieu
hal.structure.identifierAnalysis and Control of Unsteady Models for Engineering Sciences [ACUMES]
dc.contributor.authorDUVIGNEAU, Régis
hal.structure.identifierLaboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur [LIMSI]
dc.contributor.authorLE MAITRE, Olivier
hal.structure.identifierK-Epsilon
hal.structure.identifierGroupama-Team France
hal.structure.identifierSirli Innovations [Pornichet]
dc.contributor.authorDURAND, Mathieu
hal.structure.identifierMyCFD
hal.structure.identifierAlgebRe, geOmetrie, Modelisation et AlgoriTHmes [AROMATH]
dc.contributor.authorBERRINI, Elisa
hal.structure.identifierInstitut de Recherche de l'Ecole Navale [IRENAV]
dc.contributor.authorHAUVILLE, Frédéric
hal.structure.identifierInstitut de Recherche de l'Ecole Navale [IRENAV]
dc.contributor.authorASTOLFI, Jacques-André
dc.date.accessioned2021-05-14T09:46:22Z
dc.date.available2021-05-14T09:46:22Z
dc.date.issued2018-10
dc.identifier.issn1615-147X
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/76999
dc.description.abstractEnGaussian-Process based optimization methods have become very popular in recent years for the global optimization of complex systems with high computational costs. These methods rely on the sequential construction of a statistical surrogate model, using a training set of computed objective function values, which is refined according to a prescribed infilling strategy. However, this sequential optimization procedure can stop prematurely if the objective function cannot be computed at a proposed point. Such a situation can occur when the search space encompasses design points corresponding to an unphysical configuration, an ill-posed problem, or a non-computable problem due to the limitation of numerical solvers. To avoid such a premature stop in the optimization procedure, we propose to use a classification model to learn non-computable areas and to adapt the infilling strategy accordingly. Specifically, the proposed method splits the training set into two subsets composed of computable and non-computable points. A surrogate model for the objective function is built using the training set of computable points, only, whereas a probabilistic classification model is built using the union of the computable and non-computable training sets. The classifier is then incorporated in the surrogate-based optimization procedure to avoid proposing new points in the non-computable domain while improving the classification uncertainty if needed. The method has the advantage to automatically adapt both the surrogate of the objective function and the classifier during the iterative optimization process. Therefore, non-computable areas do not need to be a priori known. The proposed method is applied to several analytical problems presenting different types of difficulty, and to the optimization of a fully nonlinear fluid-structure interaction system. The latter problem concerns the drag minimization of a flexible hydrofoil with cavitation constraints. The efficiency of the proposed method compared favorably to a reference evolutionary algorithm, except for situations where the feasible domain is a small portion of the design space.
dc.language.isoen
dc.publisherSpringer Verlag (Germany)
dc.title.enA Classification Approach to Efficient Global Optimization in Presence of Non-Computable Domains
dc.typeArticle de revue
dc.identifier.doi10.1007/s00158-018-1981-8
dc.subject.halSciences de l'ingénieur [physics]/Mécanique [physics.med-ph]/Mécanique des fluides [physics.class-ph]
dc.subject.halMathématiques [math]/Optimisation et contrôle [math.OC]
dc.subject.halMathématiques [math]/Equations aux dérivées partielles [math.AP]
dc.subject.halInformatique [cs]/Analyse numérique [cs.NA]
bordeaux.journalStructural and Multidisciplinary Optimization
bordeaux.page1537 - 1557
bordeaux.volume58
bordeaux.hal.laboratoriesInstitut de Mécanique et d’Ingénierie de Bordeaux (I2M) - UMR 5295*
bordeaux.issue4
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.institutionINRAE
bordeaux.institutionArts et Métiers
bordeaux.peerReviewedoui
hal.identifierhal-01877105
hal.version1
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-01877105v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Structural%20and%20Multidisciplinary%20Optimization&rft.date=2018-10&rft.volume=58&rft.issue=4&rft.spage=1537%20-%201557&rft.epage=1537%20-%201557&rft.eissn=1615-147X&rft.issn=1615-147X&rft.au=SACHER,%20Matthieu&DUVIGNEAU,%20R%C3%A9gis&LE%20MAITRE,%20Olivier&DURAND,%20Mathieu&BERRINI,%20Elisa&rft.genre=article


Fichier(s) constituant ce document

FichiersTailleFormatVue

Il n'y a pas de fichiers associés à ce document.

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée