Application of Cokriging Technique to Structural Reliability Analysis

Approximation techniques are widely used in structural reliability analysis to build computationally inexpensive surrogate models to replace expensive-to-run computer analysis codes. Recently, kriging models are frequently utilized to construct surrogate approximations; however, they may be inefficient for systems having with a large number of design variables. Therefore, a new method-cokriging, which is an extension of kriging for creating surrogate models, is proposed for large-scale systems. In this paper, our intention is to discuss the suitability of cokriging models for structural reliability analysis, especially in high-dimensional problems. First, This paper explores the use of the cokriging method for structural reliability problems by comparing it with the kriging method based on two numerical examples. Secondly, comparisons between the two different database augmenting schemes in the cokriging models are made based on the examples. Finally, this paper suggests the points for which the cokriging model could be improved to get better results for structural reliability problems.