上海交通大学学报 ›› 2022, Vol. 56 ›› Issue (7): 937-943.doi: 10.16183/j.cnki.jsjtu.2021.179

• 交通运输工程 • 上一篇    下一篇

自适应采样方法在船型优化中的应用

欧阳旭宇, 常海超(), 刘祖源, 冯佰威, 詹成胜, 程细得   

  1. 武汉理工大学 a.高性能船舶技术教育部重点实验室; b.船海与能源动力工程学院,武汉 430063
  • 收稿日期:2021-05-27 出版日期:2022-07-28 发布日期:2022-08-16
  • 通讯作者: 常海超 E-mail:361169473@163.com.
  • 作者简介:欧阳旭宇(1997-),男,湖南省涟源市人,硕士生,从事船型优化及近似技术研究.
  • 基金资助:
    国家自然科学基金(51720105011);国家自然科学基金(51979211);高性能船舶技术教育部重点实验室开放基金(gxnc19051804);湖北省重点研发计划(2021BID008)

Application of Adaptive Sampling Method in Hull Form Optimization

OUYANG Xuyu, CHANG Haichao(), LIU Zuyuan, FENG Baiwei, ZHAN Chengsheng, CHENG Xide   

  1. a. Key Laboratory of High Performance Ship Technology of the Ministry of Education; b. School of Naval Architecture, Ocean and Energy Power Engineering, Wuhan University of Technology, Wuhan 430063, China
  • Received:2021-05-27 Online:2022-07-28 Published:2022-08-16
  • Contact: CHANG Haichao E-mail:361169473@163.com.

摘要:

为了解决船型优化中仿真计算复杂耗时的问题,基于自适应采样的近似模型技术的应用日益广泛.基于Kriging近似模型和留一法误差,发展了一种基于均匀设计的最大熵自适应采样方法.通过与基于增量拉丁超立方方法进行对比,所提方法得到的自适应样本分布更加均匀,并且其全局近似模型精度更高.将所提方法应用于S60的船型优化中,很好地验证了该方法的有效性.

关键词: 船型优化, 自适应采样, 均匀设计, 最大熵采样

Abstract:

In order to handle the problem of complex and time-consuming simulation calculation in hull form optimization, the approximate model based on adaptive sampling has been widely used. In this paper, a maximum entropy (ME) adaptive sampling method based on uniform design (UD) is developed based on the Kriging approximate model and the leave-one-out (LOO) error method. Compared with the incremental Latin hypercube design (LHD) method, the adaptive sample distribution obtained by the proposed method are more uniform, and the accuracy of the global approximation model is higher. The proposed method is applied to the S60 hull form optimization, and the effectiveness is verified.

Key words: hull form optimization, adaptive sampling, uniform design (UD), maximum entropy (ME) sampling

中图分类号: