Using meta-models as fast and accurate predictors of a reconfigurable mould system

In this paper methods from the meta- or surrogate modeling literature are used to build models for predicting the response of a reconfigurable mould system. The proposed methods are difference methods constructed from the methods kriging and proper orthogonal decomposition (POD) together with a spline-based coarse model. Four different models, namely kriging and POD with kriging of the coefficients in global and local variants, are compared in terms of accuracy and numerical efficiency on data sets of different sizes. It is shown that the POD methods are vastly superior for the treated problem.