Kriging models for global approximation in simulation-based multidisciplinary design optimization

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

Research output: Contribution to journalArticle

735 Citations (Scopus)

Abstract

Response surface methods have been used for a variety of applications in aerospace engineering, particularly in multidisciplinary design optimization. We investigate the use of kriging models as alternatives to traditional second-order polynomial response surfaces for constructing global approximations for use in a real aerospace engineering application, namely, the design of an aerospike nozzle. Our objective is to examine the difficulties in building and using kriging models to create accurate global approximations to facilitate multidisciplinary design optimization. Error analysis of the response surface and kriging models is performed, along with a graphical comparison of the approximations. Four optimization problems are also formulated and solved using both sets of approximation models to gain insight into their use for multidisciplinary design optimization. We find that the kriging models, which use only a constant "global" model and a Gaussian correlation function, yield global approximations that are slightly more accurate than the response surface models.

Original languageEnglish (US)
Pages (from-to)2233-2241
Number of pages9
JournalAIAA journal
Volume39
Issue number12
DOIs
StatePublished - Jan 1 2001

Fingerprint

Aerospace engineering
Design optimization
Error analysis
Nozzles
Polynomials

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering

Cite this

Simpson, Timothy William ; Mauery, Timothy M. ; Korte, John J. ; Mistree, Farrokh. / Kriging models for global approximation in simulation-based multidisciplinary design optimization. In: AIAA journal. 2001 ; Vol. 39, No. 12. pp. 2233-2241.
@article{0a96e6fa149c4cd9a2992a9804b116d2,
title = "Kriging models for global approximation in simulation-based multidisciplinary design optimization",
abstract = "Response surface methods have been used for a variety of applications in aerospace engineering, particularly in multidisciplinary design optimization. We investigate the use of kriging models as alternatives to traditional second-order polynomial response surfaces for constructing global approximations for use in a real aerospace engineering application, namely, the design of an aerospike nozzle. Our objective is to examine the difficulties in building and using kriging models to create accurate global approximations to facilitate multidisciplinary design optimization. Error analysis of the response surface and kriging models is performed, along with a graphical comparison of the approximations. Four optimization problems are also formulated and solved using both sets of approximation models to gain insight into their use for multidisciplinary design optimization. We find that the kriging models, which use only a constant {"}global{"} model and a Gaussian correlation function, yield global approximations that are slightly more accurate than the response surface models.",
author = "Simpson, {Timothy William} and Mauery, {Timothy M.} and Korte, {John J.} and Farrokh Mistree",
year = "2001",
month = "1",
day = "1",
doi = "10.2514/2.1234",
language = "English (US)",
volume = "39",
pages = "2233--2241",
journal = "AIAA Journal",
issn = "0001-1452",
publisher = "American Institute of Aeronautics and Astronautics Inc. (AIAA)",
number = "12",

}

Kriging models for global approximation in simulation-based multidisciplinary design optimization. / Simpson, Timothy William; Mauery, Timothy M.; Korte, John J.; Mistree, Farrokh.

In: AIAA journal, Vol. 39, No. 12, 01.01.2001, p. 2233-2241.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Kriging models for global approximation in simulation-based multidisciplinary design optimization

AU - Simpson, Timothy William

AU - Mauery, Timothy M.

AU - Korte, John J.

AU - Mistree, Farrokh

PY - 2001/1/1

Y1 - 2001/1/1

N2 - Response surface methods have been used for a variety of applications in aerospace engineering, particularly in multidisciplinary design optimization. We investigate the use of kriging models as alternatives to traditional second-order polynomial response surfaces for constructing global approximations for use in a real aerospace engineering application, namely, the design of an aerospike nozzle. Our objective is to examine the difficulties in building and using kriging models to create accurate global approximations to facilitate multidisciplinary design optimization. Error analysis of the response surface and kriging models is performed, along with a graphical comparison of the approximations. Four optimization problems are also formulated and solved using both sets of approximation models to gain insight into their use for multidisciplinary design optimization. We find that the kriging models, which use only a constant "global" model and a Gaussian correlation function, yield global approximations that are slightly more accurate than the response surface models.

AB - Response surface methods have been used for a variety of applications in aerospace engineering, particularly in multidisciplinary design optimization. We investigate the use of kriging models as alternatives to traditional second-order polynomial response surfaces for constructing global approximations for use in a real aerospace engineering application, namely, the design of an aerospike nozzle. Our objective is to examine the difficulties in building and using kriging models to create accurate global approximations to facilitate multidisciplinary design optimization. Error analysis of the response surface and kriging models is performed, along with a graphical comparison of the approximations. Four optimization problems are also formulated and solved using both sets of approximation models to gain insight into their use for multidisciplinary design optimization. We find that the kriging models, which use only a constant "global" model and a Gaussian correlation function, yield global approximations that are slightly more accurate than the response surface models.

UR - http://www.scopus.com/inward/record.url?scp=0035659213&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035659213&partnerID=8YFLogxK

U2 - 10.2514/2.1234

DO - 10.2514/2.1234

M3 - Article

VL - 39

SP - 2233

EP - 2241

JO - AIAA Journal

JF - AIAA Journal

SN - 0001-1452

IS - 12

ER -