点击次数：

论文类型：期刊论文

发表时间：2020-02-15

发表刊物：OCEAN ENGINEERING

收录刊物：EI、SCIE

卷号：198

ISSN号：0029-8018

关键字：Sequential sampling; Meta-modeling; SWATH; Design optimization; Numerical simulation

摘要：This paper proposes an improved sequential sampling approach for meta-modeling to surrogate computationally expensive simulations during the SWATH design optimization. Starting from an initial training set, a series of new samples are sequentially selected in important Voronoi cells based on the Voronoi diagram. The method is applied on an eight-variable total resistance optimization of a 32 m SWATH in calm water at lan. The metamodel of total resistance with required accuracy is generated by the proposed method and applied on the optimization process. The sampling results have shown the effectiveness of the proposed sampling method and the advantage of the meta-model that achieve the required accuracy with relatively small samples, which are meaningful for high-dimensional SWATH shape optimization.