基于并行EGO算法的激波控制鼓包减阻优化  

Shock Control Bump Optimization for Drag Reduction Using Parallel Efficient Global Optimization Algorithm

作　　者：邓枫[1] 覃宁[1,2] 伍贻兆[1] 

机构地区：[1]南京航空航天大学飞行器先进设计技术国防重点学科实验室,南京210016 [2]Department of Mechanical Engineering University of Sheffield,Sheffield S1 3JD,UK

出　　处：《南京航空航天大学学报》2013年第4期485-490,共6页Journal of Nanjing University of Aeronautics & Astronautics

基　　金：中央高校基本科研业务费专项科研(NJ2011002)资助项目;江苏高校优势学科建设工程资助项目

摘　　要：建立了并行EGO全局优化算法框架,并将其应用于二维和三维激波控制鼓包减阻优化设计当中。EGO全局优化算法是一类基于克里金(Kriging)代理模型的全局优化算法,具有自动平衡全局搜索与局部搜索的优点,适合于处理具有少量设计参数但是函数计算耗时很长的优化问题,例如基于计算流体力学的气动优化设计。为考察并行EGO全局优化算法的效率,选用了4个解析优化算例以及二维和三维激波控制鼓包减阻优化问题对克里金信任法、常数取代法以及罚点法等3种启发式并行策略进行了比较。数值实验表明,并行EGO全局优化算法每次取点个数可多达16个之多,加速将近16倍,其中在3种并行策略中又以罚点法效率最高,因而在计算耗时很长的气动外形优化问题当中具有很大的应用前景。The parallel efficient global optimization （EGO） algorithm is applied to the 2D/3D shock con trol bump optimizations. The EGO algorithm is a global optimization method based on the Kriging mod el, which is especially designed for expensive black box functions, such as highfidelity aerodynamic shape optimizations. Three heuristic parallel strategies including ＂Kriging believer＂, ＂constant liar＂ and ＂ imputed point＂ strategies are investigated based on four benchmark optimization problems and two shock control bump optimization problems. In shock control bump optimization problems, the parallel EGO algorithm is nearly 16 times faster than the serial EGO algorithm. And our research als0 shows that ＇ Imputed pointI strategy is the best strategy in these optimization problems.

关 键 词：计算流体力学 气动外形优化 激波控制鼓包 全局优化 并行计算 

分 类 号：V211.3[航空宇航科学与技术—航空宇航推进理论与工程]