Optimization of Highly Non-Linear Simulation Functions Using Improved Adaptive Response Surface Methodology

Abstract:

Adaptive Response Surface Methodology (ARSM) is a new developed method sequentially estimates the optimum of a complex function in a gradually reduced design space. In this paper, previously developed approach in ARSM has been compare and contrast with a new approach proposed by authors: using inherited Latin Hypercube Design (LHD) points and generating new Maximin LHD points by solving facility location problems in each iteration. Minimum of the response surface which is a second order approximate model based on LHD points in each iteration is an estimation of the real optimum of the complex function. The computation results reveal that the new suggested approach demonstrate more precise estimation of minimum with less number of function calls compare to the ARSM with random LHDs which is an improvement in the efficiency and accuracy of ARSM.

• Periodical: Applied Mechanics and Materials (Volumes 110-116)
• Pages: 2662-2669
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.110-116.2662
• Online since: October 2011
• Authors: Mojdeh Shirazi Manesh, Seyed Mohammadali Motavallian, Parviz Fattahi
• Keywords: Adaptive Response Surface Methodology, Computation-Intensive Design Problems, Latin Hypercube Design, Optimum

References

[1] T. W. Simpson, D. K. J. Lin, W. Chen, Sampling strategies for computer experiments: Design and analysis, International Journal of Reliability and Applications, vol. 2(3), pp.209-240, (2001).

[2] D. C. Montgomery, Design and Analysis of Experiments, Fourth Edition, John Wiley & Sons, New York, (1997).

[3] G. E. P. Box, N. R. Draper, Empirical model building and response surfaces, John Wiley & Sons, New York, (1987).

[4] R. H. Myers, D. C. Montgomery, Response Surface Methodology: Process and Product Optimization Using Designed Experiments, John Wiley & Sons, New York, (1995).

[5] G. Wang,Z. Dong and P. Aitchison, Adaptive Response Surface Method — A Global Optimization Scheme for Computation-intensive Design Problems, Journal of Engineering Optimization, Vol. 33, No. 6, pp.707-734, (2001).

DOI: 10.1080/03052150108940940

[6] M. Smith, Neural Networks for Statistical Modeling, von Nostrand Reinhold, New York, (1993).

[7] J. Sacks, S.B. Schiller, W.J. Welch, Designs for computer experiments, Technometrics, Vol. 31, pp.41-47, (1989).

DOI: 10.1080/00401706.1989.10488474

[8] J. H. Friedman, Multivariate adaptive regression splines, The Annals of Statistics, Vol. 19, No. 1, pp.1-67, (1991).

[9] N. Dyn, D. Levin, and S. Rippa, Numerical procedures for surface Fitting of Scattered Data by Radial Basis Functions, SIAM Journal, Vol. 7, No. 2, pp.639-659, (1986).

DOI: 10.1137/0907043

[10] G. E. P. Box, K. B. Wilson, On the experimental attainment of optimal conditions, Journal of the Royal Statistical Society, Vol. Series B, 13, pp.1-38 (with Discussion), (1951).

[11] D. J. Finney, Fractional replication of factorial arrangements., Annals of Eugenics 12, 291–301, (1945).

DOI: 10.1111/j.1469-1809.1943.tb02333.x

[12] M.E. ‏ Johnson, L.M. Moore , D. Ylvisaker , Minimax and Maximin distance Designs, Journal of Statistical Planning and Inference, vol. 26, pp.131-148, (1990).

DOI: 10.1016/0378-3758(90)90122-b

[13] M. D. Morris, T. J. Mitchell, Exploratory designs for computer experiments, Journal of Statistical Planning and Inference, vol. 43, pp.381-402, (1995).

DOI: 10.1016/0378-3758(94)00035-t

[14] B.G.M. Husslage, G. Rennen, E.R. Dam, D. Hertog, D. Den, Space-filling latin hypercube designs for computer experiments, Center Discussion Paper 2006-18, Tilburg University, Netherlands. (2006).

DOI: 10.2139/ssrn.895464

[15] P. Audze, V. Eglais, New approach for planning out of experiments., Problems of Dynamics and Strengths, vol. 35, pp.104-107, (1977).

[16] M.D. McKay, R.J. Beckman, W.J. Conover, A comparison of three methods for selecting values of input variables in the analysis of output from a computer code, Technometrics, vol. 16, pp.239-245, (1979).

DOI: 10.1080/00401706.1979.10489755

[17] F.M. Alam,K. R. McNaught, T. J. Ringrose, A comparison of experimental designs in the development of a neural network simulation metamodel., Simulation Modelling: Practice and Theory, 12(7-8), pp.559-578, (2004).

DOI: 10.1016/j.simpat.2003.10.006

[18] G. G. Wang , Adaptive Response Surface Method Using Inherited Latin Hypercube Design Points, Transactions of ASME, Journal of Mechanical Design, pp.210-220, (2003).

DOI: 10.1115/1.1561044

[19] L. Dixon, and G. Szegö, The global optimization problem: An Introduction. Toward Global Optimization, 2 Ed, North-Holland, New York, pp.1-15, (1978).