Efficient high-dimensional metamodeling strategy using selectively high-ordered kriging HDMR (SH-K-HDMR)

다국어 초록 (Multilingual Abstract)

Selectively high-ordered kriging high dimension model representation (SH-KHDMR) is proposed for efficient metamodeling of high-dimensional, expensive, blackbox (HEB) problems. SH-K-HDMR is a kind of cut HDMR, which selectively models high order interaction components. SH-K-HDMR starts with two groups of samples, which are for HDMR and model accuracy assessment, respectively. Variance of kriging prediction error is used for sequential sampling, and an interaction measureij H is suggested and used to choose high order interaction components of cut HDMR to be modeled. The group of samples for model accuracy assessment is also used for surrogate modeling at the end of the metamodeling process, to eliminate waste of samples. Performance of the SH-K-HDMR is compared to conventional metamodeling methods, namely full-dimension kriging and kriging-HDMR. The comparison study shows that SH-K-HDMR is superior when applied to high-dimensional and nonlinear engineering problems with strong interactions between variables.

참고문헌 (Reference)

1 T. Kim, "Water impact of a surface patterned disk" 915 : A52-, 2021

2 S. Shan, "Survey of modeling and optimization strategies to solve high-dimensional design problems with computationally-expensive black-box functions" 41 : 219-241, 2010

3 I. M. Sobol, "Sensitivity estimates for nonlinear mathematical models" 1 : 407-414, 1993

4 J. E. Oakley, "Probabilistic sensitivity analysis of complex models: a Bayesian approach" 66 : 751-769, 2004

5 H. Wackernagel, "Multivariable Geostatistics: An Introduction with Applications" Springer 2003

6 S. Shan, "Metamodeling for high dimensional simulation-based design problems" 132 : 051009-, 2010

7 H. Rabitz, "General foundations of high dimensional model representations" 25 : 197-233, 1999

8 K. Kang, "Efficient high-dimensional metamodeling strategy using recursive decomposition coupled with sequential sampling method" 63 : 375-390, 2021

9 R. Jin, "Comparative studies of metamodeling techniques under multiple modelling criteria" 23 : 1-13, 2001

10 M. D. Morris, "Bayesian design and analysis of computer experiments: use of derivatives in surface prediction" 35 : 243-255, 1993

11 S. N. Lophaven, "Aspects of the Matlab Toolbox DACE" Informatics and Mathematical Modelling, Technical University of Denmark 2002

12 H. Liu, "An adaptive Bayesian sequential sampling approach for global metamodeling" 138 : 011404-, 2016

13 E. Li, "Alternative kriging-HDMR optimization method with expected improvement sampling strategy" 34 : 1807-1828, 2017

14 L. Tang, "Advanced high strength steel springback optimization by projection-based heuristic global search algorithm" 43 : 426-437, 2013

15 A. Garbo, "A model-independent adaptive sequential sampling technique based on response nonlinearity estimation" 61 : 1051-1069, 2020

16 Q. Zhang, "A model for the low cycle fatigue life prediction of discontinuously reinforced MMCs" 27 : 417-427, 2005