Maximizing Design Confidence in Sequential Simulation Based OptimizationSource: Journal of Mechanical Design:;2013:;volume( 135 ):;issue: 008::page 81004Author:Li, Jing
,
Mourelatos, Zissimos P.
,
Kokkolaras, Michael
,
Papalambros, Panos Y.
,
Gorsich, David J.
DOI: 10.1115/1.4024470Publisher: The American Society of Mechanical Engineers (ASME)
Abstract: Computational simulation models support a rapid design process. Given model approximation and operating conditions uncertainty, designers must have confidence that the designs obtained using simulations will perform as expected. The traditional approach to address this need consists of model validation efforts conducted predominantly prior to the optimization process. We argue that model validation is too daunting of a task to be conducted with meaningful success for design optimization problems associated with highdimensional space and parameter spaces. In contrast, we propose a methodology for maximizing confidence in designs generated during the simulationbased optimization process. Specifically, we adopt a trustregionlike sequential optimization process and utilize a Bayesian hypothesis testing technique to quantify model confidence, which we maximize by calibrating the simulation model within local domains if and when necessary. This ensures that the design iterates generated during the sequential optimization process are associated with maximized confidence in the utilized simulation model. The proposed methodology is illustrated using a cantilever beam design subject to vibration.
|
Collections
Show full item record
contributor author | Li, Jing | |
contributor author | Mourelatos, Zissimos P. | |
contributor author | Kokkolaras, Michael | |
contributor author | Papalambros, Panos Y. | |
contributor author | Gorsich, David J. | |
date accessioned | 2017-05-09T01:00:57Z | |
date available | 2017-05-09T01:00:57Z | |
date issued | 2013 | |
identifier issn | 1050-0472 | |
identifier other | md_135_8_081004.pdf | |
identifier uri | http://yetl.yabesh.ir/yetl/handle/yetl/152533 | |
description abstract | Computational simulation models support a rapid design process. Given model approximation and operating conditions uncertainty, designers must have confidence that the designs obtained using simulations will perform as expected. The traditional approach to address this need consists of model validation efforts conducted predominantly prior to the optimization process. We argue that model validation is too daunting of a task to be conducted with meaningful success for design optimization problems associated with highdimensional space and parameter spaces. In contrast, we propose a methodology for maximizing confidence in designs generated during the simulationbased optimization process. Specifically, we adopt a trustregionlike sequential optimization process and utilize a Bayesian hypothesis testing technique to quantify model confidence, which we maximize by calibrating the simulation model within local domains if and when necessary. This ensures that the design iterates generated during the sequential optimization process are associated with maximized confidence in the utilized simulation model. The proposed methodology is illustrated using a cantilever beam design subject to vibration. | |
publisher | The American Society of Mechanical Engineers (ASME) | |
title | Maximizing Design Confidence in Sequential Simulation Based Optimization | |
type | Journal Paper | |
journal volume | 135 | |
journal issue | 8 | |
journal title | Journal of Mechanical Design | |
identifier doi | 10.1115/1.4024470 | |
journal fristpage | 81004 | |
journal lastpage | 81004 | |
identifier eissn | 1528-9001 | |
tree | Journal of Mechanical Design:;2013:;volume( 135 ):;issue: 008 | |
contenttype | Fulltext |