The effect of the type and parameter of the radial basis function on the performance of metamodel-based sequential global optimization

Abstract

Metamodel-based sequential global optimization (SGO) aims for finding the global optimum with a relatively small number of sample design points where expensive simulations are performed, and widely used for industrial design problems. As a metamodel-based SGO, “Constrained Optimization By Radial basis function interpolation” (COBRA) has been proposed using a cubic radial basis function (RBF) with a linear polynomial tail as the metamodel. In this study, we investigated the effect of the type and parameter of the RBF on the performance of metamodel-based SGO with comparing the original test results. Then, we recommended RBF type and parameter with the best performance for the mathematical and engineering test problems representing various practical optimization problems.