Constrained effcient global optimization with probabilistic support vector machines

Anirban Basudhar, Sylvain Lacaze, Samy Missoum

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations

Abstract

This paper presents a methodology for constrained effcient global optimization (EGO) using support vector machines (SVMs). The proposed SVM-based method has several advantages. It is more general because it is applicable to a wider variety of problems compared to current techniques. These include problems with discontinuous and binary (pass/fail) states and multiple constraints. In this paper, the objective function is ap- proximated using Kriging while the constraint boundary is approximated using an SVM classifier. The probability of misclassification by the SVM is calculated using a probabilistic support vector machine (PSVM). The existing PSVM models have certain limitations that make them unsuitable for application in the proposed methodology. Therefore, a modified PSVM model is also proposed to overcome these limitations. Several constrained EGO for- mulations are implemented and compared in this paper. The results are also compared to EGO implementations with Kriging-based constraint approximations from the literature.

Original languageEnglish (US)
Title of host publication13th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference 2010
DOIs
StatePublished - 2010
Externally publishedYes
Event13th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference, MAO 2010 - Ft. Worth, TX, United States
Duration: Sep 13 2010Sep 15 2010

Publication series

Name13th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference 2010

Other

Other13th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference, MAO 2010
Country/TerritoryUnited States
CityFt. Worth, TX
Period9/13/109/15/10

ASJC Scopus subject areas

  • Aerospace Engineering
  • Mechanical Engineering

Fingerprint

Dive into the research topics of 'Constrained effcient global optimization with probabilistic support vector machines'. Together they form a unique fingerprint.

Cite this