Cross-validation based single response adaptive design of experiments for Kriging metamodeling of deterministic computer simulations

Authors:
V. Aute;K. Saleh;O. Abdelaziz;S. Azarm;R. Radermacher
Affiliations:
Mechanical Engineering Department, University of Maryland, College Park, USA 20742;Mechanical Engineering Department, University of Maryland, College Park, USA 20742;Oak Ridge National Lab, Oak Ridge, USA 37831;Mechanical Engineering Department, University of Maryland, College Park, USA 20742;Mechanical Engineering Department, University of Maryland, College Park, USA 20742
Venue:
Structural and Multidisciplinary Optimization
Year:
2013

Citing 8
Cited 0

An efficient sampling technique for off-line quality control

Technometrics
Response Surface Methodology: Process and Product in Optimization Using Designed Experiments

Response Surface Methodology: Process and Product in Optimization Using Designed Experiments
Multi-Objective Optimization Using Evolutionary Algorithms

Multi-Objective Optimization Using Evolutionary Algorithms
Efficient Global Optimization of Expensive Black-Box Functions

Journal of Global Optimization
A Taxonomy of Global Optimization Methods Based on Response Surfaces

Journal of Global Optimization
A new metric for measuring metamodels quality-of-fit for deterministic simulations

Proceedings of the 38th conference on Winter simulation
Hierarchical Nonlinear Approximation for Experimental Design and Statistical Data Fitting

SIAM Journal on Scientific Computing
ParEGO: a hybrid algorithm with on-line landscape approximation for expensive multiobjective optimization problems

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new approach for single response adaptive design of deterministic computer experiments is presented. The approach is called SFCVT, for Space-Filling Cross-Validation Tradeoff. SFCVT uses metamodeling to obtain an estimate of cross-validation errors, which are maximized subject to a constraint on space filling to determine sample points in the design space. The proposed method is compared, using a test suite of forty four numerical examples, with three DOE methods from the literature. The numerical test examples can be classified into symmetric and asymmetric functions. Symmetric examples refer to functions for which the extreme points are located symmetrically in the design space and asymmetric examples are those for which the extreme regions are not located in a symmetric fashion in the design space. Based upon the comparison results for the numerical examples, it is shown that SFCVT performs better than an existing adaptive and a non-adaptive DOE method for asymmetric multimodal functions with high nonlinearity near the boundary, and is comparable for symmetric multimodal functions and other test problems. The proposed approach is integrated with a multi-scale heat exchanger optimization tool to reduce the computational effort involved in the design of novel air-to-water heat exchangers. The resulting designs are shown to be significantly more compact than mainstream heat exchanger designs.