Comparison of response surface and kriging models for multidisciplinary design optimization

Timothy W. Simpson, Timothy M. Mauery, John J. Korte, Farrokh Mistree

Research output: Contribution to conferencePaper

243 Citations (Scopus)

Abstract

In this paper, we compare and contrast the use of second-order response surface models and kriging models for approximating non-random, deterministic computer analyses. After reviewing the response surface method for constructing polynomial approximations, kriging is presented as an alternative approximation method for the design and analysis of computer experiments. Both methods are applied to the multidisciplinary design of an aerospike nozzle which consists of a computational fluid dynamics model and a finite-element model. Error analysis of the response surface and kriging models is performed along with a graphical comparison of the approximations, and four optimization problems are formulated and solved using both sets of approximation models. The second-order response surface models and kriging models—using a constant underlying global model and a Gaussian correlation function—yield comparable results.

Original languageEnglish (US)
Pages381-391
Number of pages11
StatePublished - Jan 1 1998
Event7th AIAA/USAF/NASA/ISSMO Symposium on Multidisciplinary Analysis and Optimization, 1998 - St. Louis, United States
Duration: Sep 2 1998Sep 4 1998

Other

Other7th AIAA/USAF/NASA/ISSMO Symposium on Multidisciplinary Analysis and Optimization, 1998
CountryUnited States
CitySt. Louis
Period9/2/989/4/98

Fingerprint

Polynomial approximation
Design optimization
Error analysis
Dynamic models
Nozzles
Computational fluid dynamics
Experiments

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Mechanical Engineering

Cite this

Simpson, T. W., Mauery, T. M., Korte, J. J., & Mistree, F. (1998). Comparison of response surface and kriging models for multidisciplinary design optimization. 381-391. Paper presented at 7th AIAA/USAF/NASA/ISSMO Symposium on Multidisciplinary Analysis and Optimization, 1998, St. Louis, United States.
Simpson, Timothy W. ; Mauery, Timothy M. ; Korte, John J. ; Mistree, Farrokh. / Comparison of response surface and kriging models for multidisciplinary design optimization. Paper presented at 7th AIAA/USAF/NASA/ISSMO Symposium on Multidisciplinary Analysis and Optimization, 1998, St. Louis, United States.11 p.
@conference{36f0b42e004f45ed9bc4cea2b531e805,
title = "Comparison of response surface and kriging models for multidisciplinary design optimization",
abstract = "In this paper, we compare and contrast the use of second-order response surface models and kriging models for approximating non-random, deterministic computer analyses. After reviewing the response surface method for constructing polynomial approximations, kriging is presented as an alternative approximation method for the design and analysis of computer experiments. Both methods are applied to the multidisciplinary design of an aerospike nozzle which consists of a computational fluid dynamics model and a finite-element model. Error analysis of the response surface and kriging models is performed along with a graphical comparison of the approximations, and four optimization problems are formulated and solved using both sets of approximation models. The second-order response surface models and kriging models—using a constant underlying global model and a Gaussian correlation function—yield comparable results.",
author = "Simpson, {Timothy W.} and Mauery, {Timothy M.} and Korte, {John J.} and Farrokh Mistree",
year = "1998",
month = "1",
day = "1",
language = "English (US)",
pages = "381--391",
note = "7th AIAA/USAF/NASA/ISSMO Symposium on Multidisciplinary Analysis and Optimization, 1998 ; Conference date: 02-09-1998 Through 04-09-1998",

}

Simpson, TW, Mauery, TM, Korte, JJ & Mistree, F 1998, 'Comparison of response surface and kriging models for multidisciplinary design optimization', Paper presented at 7th AIAA/USAF/NASA/ISSMO Symposium on Multidisciplinary Analysis and Optimization, 1998, St. Louis, United States, 9/2/98 - 9/4/98 pp. 381-391.

Comparison of response surface and kriging models for multidisciplinary design optimization. / Simpson, Timothy W.; Mauery, Timothy M.; Korte, John J.; Mistree, Farrokh.

1998. 381-391 Paper presented at 7th AIAA/USAF/NASA/ISSMO Symposium on Multidisciplinary Analysis and Optimization, 1998, St. Louis, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Comparison of response surface and kriging models for multidisciplinary design optimization

AU - Simpson, Timothy W.

AU - Mauery, Timothy M.

AU - Korte, John J.

AU - Mistree, Farrokh

PY - 1998/1/1

Y1 - 1998/1/1

N2 - In this paper, we compare and contrast the use of second-order response surface models and kriging models for approximating non-random, deterministic computer analyses. After reviewing the response surface method for constructing polynomial approximations, kriging is presented as an alternative approximation method for the design and analysis of computer experiments. Both methods are applied to the multidisciplinary design of an aerospike nozzle which consists of a computational fluid dynamics model and a finite-element model. Error analysis of the response surface and kriging models is performed along with a graphical comparison of the approximations, and four optimization problems are formulated and solved using both sets of approximation models. The second-order response surface models and kriging models—using a constant underlying global model and a Gaussian correlation function—yield comparable results.

AB - In this paper, we compare and contrast the use of second-order response surface models and kriging models for approximating non-random, deterministic computer analyses. After reviewing the response surface method for constructing polynomial approximations, kriging is presented as an alternative approximation method for the design and analysis of computer experiments. Both methods are applied to the multidisciplinary design of an aerospike nozzle which consists of a computational fluid dynamics model and a finite-element model. Error analysis of the response surface and kriging models is performed along with a graphical comparison of the approximations, and four optimization problems are formulated and solved using both sets of approximation models. The second-order response surface models and kriging models—using a constant underlying global model and a Gaussian correlation function—yield comparable results.

UR - http://www.scopus.com/inward/record.url?scp=84983139995&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983139995&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84983139995

SP - 381

EP - 391

ER -

Simpson TW, Mauery TM, Korte JJ, Mistree F. Comparison of response surface and kriging models for multidisciplinary design optimization. 1998. Paper presented at 7th AIAA/USAF/NASA/ISSMO Symposium on Multidisciplinary Analysis and Optimization, 1998, St. Louis, United States.