作者: Yang Xiaobo , Yang Fei , Cai Ziliang , Li Yuelei , Li Yaohui
DOI:
关键词: Sequential optimization 、 Mathematical optimization 、 Sampling (statistics) 、 Design of experiments 、 Computer experiment 、 Computer science 、 Reduction (complexity) 、 Dimension (vector space) 、 Model building 、 Kriging
摘要: The invention discloses an incremental Kriging based sequential optimization experiment design method. method comprises the following steps: 1, selecting initial design; 2, initially building a model and verifying model; 3, of (IKM); 4, optimizing sampling rule; 5, updating 6, through DACE (design analysis computer experiment). used for is effective, but time abruptly increases as points increase (when quantity more than 600 in case two dimension). To solve problem, improved provided, has advantage that consumption can be minimized large amount points; due to reduction time, widely applied engineering simulation.