Comparer des méthodes

	Méthodologie de surface de réponse assistée par simulation	Méthodologie Robuste de Surfaces de Réponse
Domaine	Plans d'expériences	Plans d'expériences
Famille	Process / pipeline	Process / pipeline
Année d'origine	1951 (RSM); simulation integration widely adopted from 1980s onward	1990
Auteur d'origine	Box & Wilson (RSM foundation); Kleijnen and others for simulation-based extensions	G. G. Vining and Raymond H. Myers (dual response formulation)
Type	Experimental optimization method	Experimental optimization technique
Source fondatrice	Myers, R. H., Montgomery, D. C., & Anderson-Cook, C. M. (2016). Response Surface Methodology: Process and Product Optimization Using Designed Experiments (4th ed.). Wiley. ISBN: 978-1118916025	Vining, G. G., & Myers, R. H. (1990). Combining Taguchi and response surface philosophies: A dual response approach. Journal of Quality Technology, 22(1), 38–45.
Alias	SA-RSM, simulation-based RSM, computer simulation RSM, metamodel-assisted RSM	Robust RSM, dual response surface methodology, robust parameter design via RSM, mean-variance RSM
Apparentées	6	3
Résumé	Simulation-assisted response surface methodology (SA-RSM) combines computer simulation models — such as finite element analysis, computational fluid dynamics, or discrete-event simulation — with the statistical framework of response surface methodology to efficiently map, model, and optimize system responses. Instead of running physical experiments, the researcher executes simulation runs at design points prescribed by an RSM design, fits a polynomial metamodel (surrogate) to the simulation outputs, and uses that metamodel to locate optimal factor settings.	Robust Response Surface Methodology (Robust RSM) is an experimental optimization strategy that simultaneously fits two regression models — one for the mean response and one for its variance (or standard deviation) — across a designed experiment. By jointly optimizing these dual surfaces, engineers identify factor settings that hit a performance target while minimizing process variability, combining the empirical model-building power of classical RSM with the variance-reduction goals of robust parameter design.