EGO - STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION GROUP...

Info iconThis preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION GROUP CLUDING UNCERTAINTY MODELS INCLUDING UNCERTAINTY MODELS FOR MORE EFFICIENT SURROGATE ASED DESIGN OPTIMIZATION BASED DESIGN OPTIMIZATION Raphael T. Haftka [email protected] Felipe A. C. Viana [email protected]
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
BACKGROUND: SURROGATE MODELING Surrogates replace expensive simulations in design optimization. an estimate of xample: is an estimate of . • Kriging (KRG) •P o l ynomial response surface (PRS) Example: • Support vector regression • Radial basis neural networks 2 Forrester AIJ and Keane AJ, Recent advances in surrogate-based optimization , Progress in Aerospace Sciences, Vol. 45, No. 1-3, pp. 50-79, 2009.
Background image of page 2
BACKGROUND: UNCERTAINTY Some surrogates also provide an uncertainty stimate tandard estimate : standard error, s ( x ) . Example: kriging and olynomial response polynomial response surface . These are used in EGO 3
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
MOTIVATION SURROGATE-BASED OPTIMIZATION WITH FEW CYCLES The cost and complexity of simulations encourages cycles with large number of points (less sensitive to failed simulations). p( ) There are efficient optimization algorithms that select one simulation at a 4 time based on uncertainty models. We would like to extend them to more simulations per cycle.
Background image of page 4
Outline • Efficient Global Optimization (EGO) • Importing uncertainty models in order to use GO with surrogates without uncertainty
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 6
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 06/06/2011 for the course EAS 4240 taught by Professor Peterifju during the Spring '08 term at University of Florida.

Page1 / 20

EGO - STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION GROUP...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online