Iterative Kriging-based Methods for Expensive Black-Box Models - Archive ouverte HAL
Article Dans Une Revue IEEE Transactions on Magnetics Année : 2018

Iterative Kriging-based Methods for Expensive Black-Box Models

Résumé

Reliability-Based Design Optimization (RBDO) in electromagnetic field problems requires the calculation of probability of failure leading to a huge computational cost in the case of expensive models. Three different RBDO approaches using kriging surrogate model are proposed to overcome this difficulty by introducing an approximation of the objective function and constraints. These methods use different infill sampling criteria (ISC) to add samples in the process of optimization or/and in the reliability analysis. Several enrichment criteria and strategies are compared in terms of number of evaluations and accuracy of the solution. Index Terms-Infill sampling criteria, kriging model, reliability analysis, reliability-based design optimization.
Fichier principal
Vignette du fichier
Iterative Kriging-based Methods for Expensive Black-Box Models_final version.pdf (606.27 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01913756 , version 1 (06-11-2018)

Identifiants

Citer

Siyang Deng, Reda El Bechari, Stephane Brisset, Stéphane Clenet. Iterative Kriging-based Methods for Expensive Black-Box Models. IEEE Transactions on Magnetics, 2018, 54 (3), pp.1 - 4. ⟨10.1109/TMAG.2017.2767706⟩. ⟨hal-01913756⟩
26 Consultations
81 Téléchargements

Altmetric

Partager

More