Analysis of support vector regression for approximation of complex engineering analyses

Stella M. Clarke, Timothy W. Simpson, Jan H. Griebsch

Research output: Contribution to conferencePaperpeer-review

31 Scopus citations

Abstract

A variety of metamodeling techniques have been developed in the past decade to reduce the computational expense of computer-based analysis and simulation codes. Metamodeling is the process of building a "model of a model" that provides a fast surrogate for a computationally expensive computer code. Common metamodeling techniques include response surface methodology, kriging, radial basis functions, and multivariate adaptive regression splines. In this paper, we present Support Vector Regression (SVR) as an alternative technique for approximating complex engineering analyses. The computationally efficient theory behind SVR is presented, and SVR approximations are compared against the aforementioned four metamodeling techniques using a testbed of 22 engineering analysis functions. SVR achieves more accurate and more robust function approximations than these four metamodeling techniques and shows great promise for future metamodeling applications.

Original languageEnglish (US)
Pages535-543
Number of pages9
DOIs
StatePublished - 2003
Event2003 ASME Design Engineering Technical Conferences and Computers and Information in Engineering Conference - Chicago, IL, United States
Duration: Sep 2 2003Sep 6 2003

Other

Other2003 ASME Design Engineering Technical Conferences and Computers and Information in Engineering Conference
Country/TerritoryUnited States
CityChicago, IL
Period9/2/039/6/03

All Science Journal Classification (ASJC) codes

  • General Engineering

Fingerprint

Dive into the research topics of 'Analysis of support vector regression for approximation of complex engineering analyses'. Together they form a unique fingerprint.

Cite this