Comparer des méthodes

	Méthodologie de surface de réponse assistée par optimisation	Méthodologie des surfaces de réponse à réponses multiples
Domaine	Plans d'expériences	Plans d'expériences
Famille	Process / pipeline	Process / pipeline
Année d'origine	1951 (RSM); 1980 (desirability-function optimization formalized)	1980 (Derringer & Suich desirability function); RSM roots ~1951 (Box & Wilson)
Auteur d'origine	Derringer & Suich (desirability function); Box & Wilson (RSM foundation)	Derringer & Suich (desirability function approach); Myers & Montgomery (RSM framework)
Type	Hybrid experimental-optimization framework	Experimental optimization technique
Source fondatrice	Derringer, G., & Suich, R. (1980). Simultaneous optimization of several response variables. Journal of Quality Technology, 12(4), 214–219.	Derringer, G., & Suich, R. (1980). Simultaneous optimization of several response variables. Journal of Quality Technology, 12(4), 214–219.
Alias	OA-RSM, RSM with optimization, desirability-based RSM, multi-response RSM optimization	Multi-response RSM, MRSM, Multi-objective RSM, Multiple response optimization
Apparentées	5	6
Résumé	Optimization-assisted RSM couples a second-order response surface model with a mathematical optimization routine — most commonly Derringer and Suich's desirability function, but also genetic algorithms or gradient-based solvers — to locate the factor settings that simultaneously satisfy multiple quality or performance objectives. The result is a data-driven recommendation for optimal process or product conditions, supported by a polynomial model fitted to a structured experimental design.	Multi-response Response Surface Methodology (MRSM) extends classical RSM to situations where an experiment generates two or more response variables that must be optimized simultaneously. Rather than tuning factor settings for a single output, MRSM fits a separate second-order polynomial model for each response, then combines them — most commonly via Derringer and Suich's desirability function — to find factor settings that satisfy all objectives at once.