柱状耐压结构参数化分析与多目标优化研究  

RESEARCH ON PARAMETRIC ANALYSIS AND MULTI-OBJECTIVE OPTIMIZATION OF CYLINDRICAL PRESSURE STRUCTURE

作　　者：刘峰[1] 屠超华 赵彦凯 LIU Feng;TU ChaoHua;ZHAO YanKai(College of Shipbuilding Engineering,Haerbin Engineering University,Harbin 150001,China)

机构地区：[1]哈尔滨工程大学船舶工程学院,哈尔滨150001

出　　处：《机械强度》2021年第3期601-607,共7页Journal of Mechanical Strength

基　　金：国家自然科学基金项目(51709063);国家科技重大专项子任务(2011ZX05027-005)资助。

摘　　要：为提高柱状耐压结构设计效率与性能,确定了强度及稳定性分析方法,对于初始方案进行了分析。利用Python语言针对Abaqus软件进行了二次开发,利用i Sight软件对于Abaqus进行了集成,设计了耐压结构参数化分析流程,可实现柱状耐压结构的自动建模与分析。利用最优拉丁超立方方法进行了样本点的选取,对于设计变量进行了灵敏度分析,拟合精度对比表明响应面模型的精度最高,得到了基于四阶响应面的柱状耐压结构近似模型。建立了柱状耐压结构多目标优化模型,利用第二代非支配排序遗传算法进行了求解,结果表明优化方案在重量降低的同时,极限强度得到了大幅度提升,提高了柱状耐压结构性能。In order to improve the design efficiency and performance of the cylindrical pressure structure,strength and stability analysis methods were determined,the initial scheme was analyzed. the second development of Abaqus software was carried out by using Python language,Abaqus was integrated with i Sight software,the parametric analysis flow of pressure structure was designed,could realize automatic modeling and analysis of cylindrical pressure structure. the most Latin hypercube method was used to selectting the sample points,the sensitivity analysis of the design variables were carried out,The comparison of the fitting accuracy shown that the response surface model had the highest accuracy,the approximate model of the cylindrical pressure structure based on the fourth-order response surface was obtained. the multi-objective optimization model was established,The second generation of non dominated sorting genetic algorithm was used to solving the multi-objective optimization problem,the results shown that the weight of the optimization scheme was reduced,while the ultimate strength was greatly improved,improved the performance of the cylindrical pressure structure.

关 键 词：柱状耐压结构 参数化分析 灵敏度分析 近似模型 多目标优化 

分 类 号：U661[交通运输工程—船舶及航道工程]