Numerical Optimization Using Computer Experiments
Abstract
Engineering design optimization often gives rise to problems in which expensive objective functions are minimized by derivative free methods. We propose a method for solving such problems that synthesizes ideas from the numerical optimization and computer experiment literatures. Our approach relies on kriging known function values to construct a sequence of surrogate models of the objective function that are used to guide a grid search for a minimizer. Results from numerical experiments on a standard test problem are presented.
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 01, 1997
- Accession Number
- ADA329501
Entities
People
- Michael W. Trosset
- Virginia Torczon