An Improved High-Dimensional Kriging Surrogate Modeling Method through Principal Component Dimension Reduction

The Kriging surrogate model in complex simulation problems uses as few expensive objectives possible to establish a global or local approximate interpolation. However, due the inversion of covariance correlation matrix and solving Kriging-related parameters, approximation process for high-dimensional is time consuming even impossible construct. For this reason, modeling method through principal component dimension reduction (HDKM-PCDR) proposed by considering parameters design variables model. It PCDR transform parameter vector into low-dimensional one, which used reconstruct new function. In way, consumption optimization function construction greatly reduced. Compared with original based on partial least squares, can achieve faster efficiency under premise meeting certain accuracy requirements.