Efficiency improvement of Kriging surrogate model by subset simulation in implicit expression problems

Abstract

In practical engineering and industry fields, complicated and correlated problems are often descripted by implicit expression. The Kriging model is one of the popular spatial interpolation models to surrogate the numerical relationship between input and output variables. But the efficiency of the Kriging surrogate model is limited when confronting with large databases. The subset simulation is a promising selection method to provide more important and typical samples. By the subset simulation, the Kriging surrogate model can significantly reduce the computational cost in regression, since much fewer samples are required. Besides, more reliable prediction results can be obtained because of the emphasis on the samples that are more representative in the Kriging fitting process. Examples are performed to confirm the properties of the Kriging surrogate model based on the subset simulation.

Reliability intelligence analysis of concrete arch bridge based on Kriging model and PSOSA hybrid algorithm

“…In addition, selecting and determining relevant model parameters in the Kriging model is a multivariate optimization process. The performance of the numerical optimization algorithm directly affects the accuracy and stability of the relevant model parameters, which in turn affects the performance of the Kriging model (Chu et al 2020, Qin et al 2019. Most of the current Kriging models use the pattern search method (Liu et al 2008, Li 2015 to solve the parameters of the related models.…”