Non-stationary kriging for design optimization

Download

PDF - Pre print Restricted to internal admin Download (1137Kb) | Request a copy

Description/Abstract

Traditional surrogate modeling techniques, such as kriging, have been employed quite effectively within design optimizations. However, such models can fail to accurately reproduce non-stationary responses. The following paper explores the application of non-stationary kriging to design optimization and attempts to determine its applicability with regard to the optimization of both stationary and non-stationary objective functions. A series of analytical test problems and an engineering design problem are used to compare the performance of non-stationary and adaptive partial non-stationary kriging to traditional stationary kriging.