HAL : hal-00412235, version 3

arXiv : 0909.0329

Fiche détaillée

Récupérer au format BibTeX - EndNote - TEI - RefWorks -

AStA Advances in Statistical Analysis 94 (2010) 325-339

Versions disponibles :

v1 (02-09-2009)

v2 (07-02-2010)

v3 (23-09-2010)

Latin hypercube sampling with inequality constraints

Matthieu Petelet 1, Bertrand Iooss (  Auteur correspondant ) 2, 3, Olivier Asserin 1, Alexandre Loredo 4

(2010)

In some studies requiring predictive and CPU-time consuming numerical models, the sampling design of the model input variables has to be chosen with caution. For this purpose, Latin hypercube sampling has a long history and has shown its robustness capabilities. In this paper we propose and discuss a new algorithm to build a Latin hypercube sample (LHS) taking into account inequality constraints between the sampled variables. This technique, called constrained Latin hypercube sampling (cLHS), consists in doing permutations on an initial LHS to honor the desired monotonic constraints. The relevance of this approach is shown on a real example concerning the numerical welding simulation, where the inequality constraints are caused by the physical decreasing of some material properties in function of the temperature.

1 :	CEA-Direction de l'Energie Nucléaire (CEA-DEN)
	CEA
2 :	GdR MASCOT-NUM ((Méthodes d'Analyse Stochastique des Codes et Traitements Numériques))
	CNRS : GDR3179
3 :	EDF R&D
	EDF
4 :	LRMA (EA1859)
	Université de Bourgogne

Domaine

:

Mathématiques/Statistiques Statistiques/Théorie

Mots Clés : Computer experiment – Latin hypercube sampling – Design of Experiments – Uncertainty analysis – Dependence

hal-00412235, version 3

http://hal.archives-ouvertes.fr/hal-00412235

oai:hal.archives-ouvertes.fr:hal-00412235

Contributeur : Bertrand Iooss <>

Soumis le : Mercredi 22 Septembre 2010, 08:13:17

Dernière modification le : Jeudi 21 Avril 2011, 19:14:52