Recently, Response Surface Methodology (RSM) has attracted a growing interest, along with other simulation optimization (SO) techniques, for non-parametric modeling and robust optimization of systems. In the optimization stage of this study, the authors use RSM to find optimum working conditions of a system. The authors also use discrete event simulation modeling, optimization stage integration, design of experiment (DOE) and sensitivity analysis (a) to investigate the behavior of a real paint shop production line via construction of response surface plots and (b) to reveal the influence of input variables, as well as to determine interaction effects between them. The proposed approach presents an approximation model management structure for the computation-intensive optimization problem of an automotive factory with reduced variance, computational cost and amount of effort.
DengizBAkbaySK. Computer simulation of a PCB production line: Metamodeling approach. Int J Prod Econ2000; 63: 195–205.
2.
CarsonYMariaA. Simulation optimization: Methods and applications. In: Proceedings of the 1997 winter simulation conference, Piscataway, NJ, 7–10 December 1997, pp.118–126.
3.
SafizadehMHThorntonBM. Optimization in simulation experiments using response surface methodology. Comp Indust Eng1984; 8(1): 11–27.
4.
MeidtGIBauerKWJr. A decision support system for simulation metamodel construction. Simulation1992; 59: 3183–3191.
5.
BilesWEKleijnenJPC. A Java-based simulation manager for optimization and response surface methodology in multiple-response parallel simulation. In: Proceedings of the 1999 winter simulation conference, Phoenix, AZ, 5–8 December 1999, pp.513–517.
6.
NicolaiRPDekkerRPiersmaN. Automated response surface methodology for stochastic optimization models with unknown variance. In: Proceedings of the 2004 winter simulation conference, Washington DC, 5–8 December 2004, pp.491–498.
7.
AllenTYuL. Low cost response surface methods for and from simulation optimization. In: Proceedings of the 2000 winter simulation conference, Orlando, FL, 10–13 December 2000, pp.704–714.
8.
StewartPFlemingPJMacKenzieS. On the RSM and designed experiments for computationally intensive distributed aerospace simulations. In: Proceedings of the 2002 winter simulation conference, San Diego, CA, 8–11 December 2002, pp.476–482.
9.
KenneJPGharbiNA. A simulation optimization approach in production planning of failure prone manufacturing systems. J Intell Man2001; 12: 421–431.
10.
AngünMEKleijnenJPCHertogD. Response surface methodology revisited. In: Proceedings of the 2002 winter simulation conference, San Diego, CA, 8–11 December 2002, pp.377–383.
11.
SchamburgJBBrownDE. A generalized multiple Response Surface Methodology for complex computer simulation applications. In: Proceedings of the 2004 winter simulation conference, Washington DC, 5–8 December 2004, pp.958–966.
12.
SchamburgJBBrownDE. Simulated annealing for selection of experimental regions in RSM applications. In: Proceedings of the 2004 winter simulation conference, Washington DC, 5–8 December 2004, pp.931–940.
13.
OonSJLeeLH. The impact of ordinal on response surface methodology. In: Proceedings of the 2006 winter simulation conference, Monterey, CA, 3–6 December, pp.406–413.
14.
ChangK-HHongLJWanH. Stochastic trust region gradient-free method (strong)—A new response-surface-based algorithm in simulation optimization. In: Proceedings of the 2007 winter simulation conference, Wahington DC, 9–12 December 2007, pp.346–354.
15.
BaysalRENelsonBLStaumJ. Response Surface Methodology for simulating hedging and trading strategies. In: Proceedings of the 2008 winter simulation conference, Miami, Fl, 7–10 December 2008, pp.629–637.
16.
DellinoGKleijnenJPCMeloniC. Robust optimization in simulation: Taguchi and Response Surface Methodology. Int J Prod Econ2010; 125(1): 52–59.
17.
KleijnenJPC. Response surface methodology for constrained simulation optimization: An overview. Simul Model Pract Th2008; 16: 50–64.
18.
YalcinkayaOBayhanGM. Modeling and optimization of average travel time for a metro line by simulation and response surface methodology. Euro J Oper Res2009; 196: 225–233.
19.
MerkuryevaGMerkuryevYVanmaeleH. Simulation based planning and optimization in multi echelon supply chains. Simul—T Soc Mod Sim2011; 87(8): 680–695.
20.
ZakerifarMBilesWEEvansGW. Kriging metamodeling in multiple objective simulation optimization. Simul—T Soc Mod Sim2011; 87(10): 843–856.
21.
KeltonDWSadowskiRPSadowskiDA. Simulation with Arena. International ed. Boston, MA: McGraw-Hill, 1998.
22.
SchmeiserB. 1982. Batch size effects in the analysis of simulation output. Oper Res1982; 30: 556–568.
23.
LawAMCarsonJS. A sequential procedure for determining the length of a steady state simulation. Oper Res1979; 27(5): 1011–1025.
24.
LawAM. Simulation Modeling and Analysis. 4th ed.Boston, MA: McGraw-Hill, 2007.
25.
BoxGEPWilsonKB. On the experimental attainment of optimum conditions. J Roy Stat Soc B1951; 13(1): 1–38.
26.
BoxGEPHunterWGHunterJS. Statistics for Experimenters: An Introduction to Design Analysis and Model Building. New York: John Wiley & Sons, 1978.
27.
FuMC. Simulation optimization. In: Proceedings of the 2001 winter simulation conference, Arlington, VA, 9–12 December 2001, pp.79–84.
28.
NeddermeijerHGvan OortmarssenGJPiersmaN. A framework for response surface methodology for simulation optimization. In: Proceedings of the 2000 winter simulation conference, Orlando, FL, 10–13 December 2000, pp.129–136.
29.
OehlertGW. Design and Analysis of Experiments: Response Surface Design. New York: WH Freeman and Company, 2000.
