使用混合代理模型的自主式水下航行器藕节壳体多目标优化  

Mixture Surrogate Model Based Structural Optimization Design of Multiple Intersecting Spheres for Automatic Undersea Vehicle

作　　者：何衍儒 宋保维[1] 曹永辉[1] 

机构地区：[1]西北工业大学航海学院,陕西西安710072

出　　处：《水下无人系统学报》2017年第5期410-417,共8页Journal of Unmanned Undersea Systems

基　　金：国家自然科学基金资助项目(51375389)

摘　　要：针对已有藕节壳体结构优化设计均为简化模型,且没有对内部有效体积进行分析的问题,文中使用非支配排序遗传算法(NSGA-II)和由径向基函数、支持向量回归函数、Kriging函数构建的混合代理模型,对自主式水下航行器(AUV)的切弧连接藕节壳体和环肋加强藕节耐压壳体进行了浮重比和内部有效体积的多目标优化,UG二次开发程序实现了藕节壳体的参数化建模,并在满足强度和稳定性要求的前提下,准确有效地获得该多目标优化问题的Pareto前沿,可为AUV壳体优化设计提供参考。To solve the problem that the existing structural optimization designs of multiple intersecting spheres are simplified models and are lack of internal effective volume analysis, this paper uses the non-dominated sorting genetic algorithm II（NSGA-II） and the mixture surrogate model constructed by radial basis function, support vector regression function and Kriging function to perform multi-objective optimization of the tangent arc connective and ring-stiffened multiple intersecting spheres of an autonomous undersea vehicle（AUV） in terms of the buoyancy-weight ratio and the internal effective volume of the spheres. Parametric modeling of the two multiple intersecting spheres are implemented using UG secondary development. The Pareto front of this multi-objective optimization problem is obtained under the constraint of satisfying maximum equivalent stress and bulking factor. This research may provide a reference for opti- mization design of AUV shell.

关 键 词：自主式水下航行器(AUV) 藕节壳体 多目标优化 混合代理模型 NSGA-Ⅱ 

分 类 号：U674.941[交通运输工程—船舶及航道工程]