A Sequential Sampling Strategy for Multiresponse Radial Basis Function

In this paper we present a sequential sampling strategy for multiresponse radial basis function. Different from traditional methods which construct a single metamodel for each scalar response independently, the proposed approach takes multiple responses simultaneously. The product of minimum distance from other current sampling sites and curvature of the site on the response surface is introduced as the accuracy index to select the next sample point. At last, an illustration example is provided to verify the effectiveness of the proposed approach.