Exclusive Content & Downloads from ASQ

Constructing Meta-Models for Computer Experiments

Summary: [This abstract is based on the authors' abstract.]

Types of computer experiments can range from computationally inexpensive simulations of electronic circuits to expensive simulations of mechanical processes. The focus here is on finite element analysis (FEA) computer experiments. Comparison is made to alternative methods that have been proposed in the experimental design literature for creating meta-models from computer experiments. Three test functions were used to compare all combinations of experimental design classes with either second-order response surface (RS) or kriging modeling methods. Additional case study-based comparisons of the accuracy of meta-models derived from computer-experiments using alternative approaches to experimentation and analysis are provided. An investigation is made into the separate interactions of choosing a class of experimental designs, selecting a number of runs, and selecting a specific design from the chosen class and number of runs with the choice of modeling method. Evaluating the accuracy of the meta-models using a random sample of equivalent experimental designs allows for the generality of the comparison to be improved.

Anyone with a subscription, including Site and Enterprise members, can access this article.

Other Ways to Access content:

Join ASQ

Join ASQ as a Full member. Enjoy all the ASQ member benefits including access to many online articles.

Subscribe to Journal of Quality Technology

Access this and ALL OTHER Journal of Quality Technology online articles. You'll also receive the print version by mail.

  • Topics:
  • Keywords: Modeling,Experiments,Kriging,Comparison,Response surfaces,Computers
  • Author: Allen, Theodore T.; Bernshteyn, Mikhail A.; Kabiri-Bamoradian, Khalil
  • Journal: Journal of Quality Technology