Selection Method of Global Model and Correlation Coefficients for Kriging Metamodel

크리깅 메타모델의 전역모델과 상관계수 선정 방법

  • 조수길 (한양대학교 대학원 자동차공학과) ;
  • 변현석 (한양대학교 대학원 자동차공학과) ;
  • 이태희 (한양대학교 기계공학부)
  • Published : 2009.08.01


Design analysis and computer experiments (DACE) model is widely used to express efficiently nonlinear responses in the field of engineering design. As a DACE model, kriging model can approximately replace a simulation model that is very expensive or highly nonlinear. The kriging model is composed of the summation of a global model and a local model representing deviation from the global model. The local model is determined by correlation coefficient with the pre-sampled points, where the accuracy and robustness of the kriging model depends on the selection of proper correlation coefficients. Therefore, to achieve the robust kriging model, the range of the correlation coefficients is explored with respect to the degrees of the global model. Based on this study we propose the proper orders of the global model and range of parameters to make accurate and robust kriging model.


  1. Matheron, G., 1963, 'Principles of Geostatistics,' Economic Geology, Vol. 58, pp. 1246~1266
  2. Sacks, J., Welch, W.J., Mitchell, T.J. and Wynn, H.P., 1989, 'Design and Analysis of Computer Experiments,' Statistical Science, Vol. 4, No.4, pp. 409~435
  3. Simpson, T.W., Mauery, T.M., Korte, J.J. and Mistree, F., 2001, 'Kriging Models for Global Approximation in Simulation-Based Multidisciplinary Design Optimization,' AIAA Journal, Vol. 39, No. 12, pp. 2234~2241
  4. Lee, T.H., Lee, C.J. and Lee, K.K., 2003, 'Shape Optimization of a CRT based on Response Surface and Kriging Metamodels,' Trans. Of KSME (A), Vol. 27, No. 30, pp. 381~386
  5. Mitchell, T.J. and Morris, M.D., 1992, 'Baysesian Design and Analysis of Computer Experiments: Two Examples,' Statistica Sinica, Vol. 2, pp. 359~379
  6. Byun, H.S., Jung, J.J. and Lee, T.H., 2007, 'Validation Technique of Kriging Model Using Integrated Mean Squared Errors and Responses,' 7th World Congress on Structural Multidisciplinary Optimization, pp. 18~23
  7. Sacks, J., Schiller, S.B. and Welch, W.J., 1989, 'Designs for Computer Experiment,' Technometrics, Vol. 31, No. 1, pp. 41~47
  8. Lee, T.H. and Jung, J.J., 2005, 'Generalized Kriging Model for Interpolation and Regression,' Trans. Of KSME (A), Vol. 29, No. 2, pp. 277~283

Cited by

  1. Weight Function-based Sequential Maximin Distance Design to Enhance Accuracy and Robustness of Surrogate Model vol.39, pp.4, 2015,
  2. An Efficient Constraint Boundary Sampling Method for Sequential RBDO Using Kriging Surrogate Model vol.40, pp.6, 2016,
  3. Efficient Robust Design Optimization Using Statistical Moments Based on Multiplicative Decomposition Method vol.36, pp.10, 2012,