基于RBF代理模型的NOBS油船货舱结构多目标优化设计  

Multi-object Optimization Design of Cargo Hold Structure of NOBS Tanker Based on RBF Agent Model

作　　者：苏绍娟 刘灿波 张祥 王国回 SU Shao-juan;LIU Can-bo;ZHANG Xiang;WANG Guo-hui(College of Naval Architecture and Ocean Engineering,Dalian Maritime University,Dalian 116026,China;Nantong COSCO KHI Ship Engineering Co Ltd,Nantong 226005,China)

机构地区：[1]大连海事大学船舶与海洋工程学院,大连116026 [2]南通中远海运川崎船舶工程有限公司,南通226005

出　　处：《武汉理工大学学报》2021年第11期35-42,共8页Journal of Wuhan University of Technology

基　　金：国家自然科学基金(51609031);中央高校基本科研业务费专项基金(3132019320)。

摘　　要：为了提高V型无压载水船的结构优化效率,采用遗传算法结合RBF代理模型对其进行尺寸优化。首先对NOBS油船结构特性进行分析,采用灵敏度分析方法筛选优化设计变量,通过最优拉丁超立方抽样选取样本点,构建设计变量和各响应的高精度RBF代理模型,然后利用遗传算法和全局响应面搜索法进行多目标全局最优化计算。对比分析优化前后的计算结果,优化后舱段重量减少了1.15%,刚度提升了4.3%,符合规范中的要求,并提高了优化设计效率,对V型无压载水船结构优化提供了参考。In order to improve the efficiency of structural optimization of V-type non ballast water ship,genetic algorithm combined with RBF agent model for size optimization.Firstly,the structural characteristics of non-ballast water ship(NOBS)tanker are analyzed,and the sensitivity analysis method is used to choose the optimal design variables and the sample points are selected by Latin hypercube sampling.And then the high-precision RBF agent model of design variables and responses is constructed.Then,the multi-objective global optimization are calculated by genetic algorithm and global response surface search method.After optimization,the weight of the cabin is reduced by 1.15%,and the stiffness is increased by 4.3%,which meets the requirements of the specification.It also improves the efficiency of optimization design and provides a reference for the structural optimization of V-type non ballast water vessel.

关 键 词：无压载水船舶 结构优化 径向基函数 代理模型 多目标优化 

分 类 号：TU674.95[建筑科学—建筑技术科学]