Statistical approximations for multidisciplinary design optimization: The problem of size

Patrick N. Koch, Timothy William Simpson, Janet K. Allen, Farrokh Mistree

Research output: Contribution to journalArticle

160 Citations (Scopus)

Abstract

Despite the steady increase of computing power and speed, the complexity of many of today's engineering analysis codes seems to keep pace with computing advances. Furthermore, the design and development of complex systems typically requires the integration of multiple disciplines and the resolution of multiple conflicting objectives. A departure from the traditional parametric design analysis and single-objective optimization approaches is necessary for the effective solution of multidisciplinary, multiobjective complex design problems that rely on computer analyses. Statistical design of experiments and response surface modeling have been used extensively to create inexpensive-to-run approximations of expensive-to-run computer analyses and combat the problem of size associated with large, multidisciplinary design problems. However, these statistical approaches also break down because of the curse of dimensionality, wherein the number of design variables becomes too large to build accurate response surfaces efficiently. Speculations have been offered in the literature regarding the manageable problem size when these approaches are employed. In this paper, the limitations of these approaches are investigated and demonstrated explicitly by pushing the limits in a large-scale design problem. The design of a high-speed civil transport aircraft wing is used to illustrate 1) the use of these statistical techniques to facilitate multidisciplinary design optimization and 2) the resulting curse of dimensionality associated with large variable design problems. Our current research efforts in system partitioning and hierarchical modeling, and kriging (an alternative statistical approximation technique) are discussed as remedies for the problem of size.

Original languageEnglish (US)
Pages (from-to)275-286
Number of pages12
JournalJournal of Aircraft
Volume36
Issue number1
DOIs
StatePublished - Jan 1 1999

Fingerprint

Transport aircraft
Design optimization
Design of experiments
Large scale systems

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering

Cite this

Koch, Patrick N. ; Simpson, Timothy William ; Allen, Janet K. ; Mistree, Farrokh. / Statistical approximations for multidisciplinary design optimization : The problem of size. In: Journal of Aircraft. 1999 ; Vol. 36, No. 1. pp. 275-286.
@article{52325c9d005a4bf7ad9e1c523c592dca,
title = "Statistical approximations for multidisciplinary design optimization: The problem of size",
abstract = "Despite the steady increase of computing power and speed, the complexity of many of today's engineering analysis codes seems to keep pace with computing advances. Furthermore, the design and development of complex systems typically requires the integration of multiple disciplines and the resolution of multiple conflicting objectives. A departure from the traditional parametric design analysis and single-objective optimization approaches is necessary for the effective solution of multidisciplinary, multiobjective complex design problems that rely on computer analyses. Statistical design of experiments and response surface modeling have been used extensively to create inexpensive-to-run approximations of expensive-to-run computer analyses and combat the problem of size associated with large, multidisciplinary design problems. However, these statistical approaches also break down because of the curse of dimensionality, wherein the number of design variables becomes too large to build accurate response surfaces efficiently. Speculations have been offered in the literature regarding the manageable problem size when these approaches are employed. In this paper, the limitations of these approaches are investigated and demonstrated explicitly by pushing the limits in a large-scale design problem. The design of a high-speed civil transport aircraft wing is used to illustrate 1) the use of these statistical techniques to facilitate multidisciplinary design optimization and 2) the resulting curse of dimensionality associated with large variable design problems. Our current research efforts in system partitioning and hierarchical modeling, and kriging (an alternative statistical approximation technique) are discussed as remedies for the problem of size.",
author = "Koch, {Patrick N.} and Simpson, {Timothy William} and Allen, {Janet K.} and Farrokh Mistree",
year = "1999",
month = "1",
day = "1",
doi = "10.2514/2.2435",
language = "English (US)",
volume = "36",
pages = "275--286",
journal = "Journal of Aircraft",
issn = "0021-8669",
publisher = "American Institute of Aeronautics and Astronautics Inc. (AIAA)",
number = "1",

}

Statistical approximations for multidisciplinary design optimization : The problem of size. / Koch, Patrick N.; Simpson, Timothy William; Allen, Janet K.; Mistree, Farrokh.

In: Journal of Aircraft, Vol. 36, No. 1, 01.01.1999, p. 275-286.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Statistical approximations for multidisciplinary design optimization

T2 - The problem of size

AU - Koch, Patrick N.

AU - Simpson, Timothy William

AU - Allen, Janet K.

AU - Mistree, Farrokh

PY - 1999/1/1

Y1 - 1999/1/1

N2 - Despite the steady increase of computing power and speed, the complexity of many of today's engineering analysis codes seems to keep pace with computing advances. Furthermore, the design and development of complex systems typically requires the integration of multiple disciplines and the resolution of multiple conflicting objectives. A departure from the traditional parametric design analysis and single-objective optimization approaches is necessary for the effective solution of multidisciplinary, multiobjective complex design problems that rely on computer analyses. Statistical design of experiments and response surface modeling have been used extensively to create inexpensive-to-run approximations of expensive-to-run computer analyses and combat the problem of size associated with large, multidisciplinary design problems. However, these statistical approaches also break down because of the curse of dimensionality, wherein the number of design variables becomes too large to build accurate response surfaces efficiently. Speculations have been offered in the literature regarding the manageable problem size when these approaches are employed. In this paper, the limitations of these approaches are investigated and demonstrated explicitly by pushing the limits in a large-scale design problem. The design of a high-speed civil transport aircraft wing is used to illustrate 1) the use of these statistical techniques to facilitate multidisciplinary design optimization and 2) the resulting curse of dimensionality associated with large variable design problems. Our current research efforts in system partitioning and hierarchical modeling, and kriging (an alternative statistical approximation technique) are discussed as remedies for the problem of size.

AB - Despite the steady increase of computing power and speed, the complexity of many of today's engineering analysis codes seems to keep pace with computing advances. Furthermore, the design and development of complex systems typically requires the integration of multiple disciplines and the resolution of multiple conflicting objectives. A departure from the traditional parametric design analysis and single-objective optimization approaches is necessary for the effective solution of multidisciplinary, multiobjective complex design problems that rely on computer analyses. Statistical design of experiments and response surface modeling have been used extensively to create inexpensive-to-run approximations of expensive-to-run computer analyses and combat the problem of size associated with large, multidisciplinary design problems. However, these statistical approaches also break down because of the curse of dimensionality, wherein the number of design variables becomes too large to build accurate response surfaces efficiently. Speculations have been offered in the literature regarding the manageable problem size when these approaches are employed. In this paper, the limitations of these approaches are investigated and demonstrated explicitly by pushing the limits in a large-scale design problem. The design of a high-speed civil transport aircraft wing is used to illustrate 1) the use of these statistical techniques to facilitate multidisciplinary design optimization and 2) the resulting curse of dimensionality associated with large variable design problems. Our current research efforts in system partitioning and hierarchical modeling, and kriging (an alternative statistical approximation technique) are discussed as remedies for the problem of size.

UR - http://www.scopus.com/inward/record.url?scp=0032715185&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032715185&partnerID=8YFLogxK

U2 - 10.2514/2.2435

DO - 10.2514/2.2435

M3 - Article

AN - SCOPUS:0032715185

VL - 36

SP - 275

EP - 286

JO - Journal of Aircraft

JF - Journal of Aircraft

SN - 0021-8669

IS - 1

ER -