서포트벡터회귀 기법을 이용한 순차적 근사 최적설계

Support Vector Regression (SVR) is getting popular due to its higher accuracy and lower standard deviation than those of existing approximate methods. However SVR has been rarely used for design optimization while it has been applied to many studies such as time series prediction, and statistical learning theory. In this study, an SAO method based on SVR developed. We adopt inherited Optimal Latin Hypercube Design (OLHD) for Design of Experiment (DOE) and Trust Region (TR) concept for model management. Finally, in order to show the accuracy and efficiency of the proposed method, several sample problems are solved.