基于遗传算法与模式搜索的混合优化算法  

A hybrid optimization method based on genetic algorithm and pattern search

作　　者：张煜东[1] 吴乐南[1] 王水花[1] 

机构地区：[1]东南大学信息科学与工程学院,南京210096

出　　处：《南京信息工程大学学报（自然科学版）》2012年第1期34-39,共6页Journal of Nanjing University of Information Science & Technology（Natural Science Edition）

基　　金：国家自然科学基金(60872075);国家863计划(2008AA01Z227);高等学校科技创新工程重大项目培育资金(706028)

摘　　要：为了更好地实现全局优化,提出一种遗传模式搜索(Genetic Pattern Search,GPS)算法,该算法结合了遗传算法(GA)的强全局搜索能力与泛化模式搜索算法(PS)的强局部搜索能力.算法流程分为两步:首先是GA与PS联合实现粗搜索;其次是PS实现细搜索.实验对Hump、Powell、Rosenbrock、Schaffer、Woods测试函数进行搜索,表明GPS算法的成功率明显优于改进遗传算法与改进模式搜索算法,可作为一种有效可行的全局优化算法.In order to realize the global optimization,a novel genetic pattern search （GPS） method is proposed in this paper, which combines the powerful global search ability of genetic algorithm （GA） and the powerful local search ability of generalized pattern search （PS）. The algorithm is two-folded, firstly GA and PS are integrated to coarse-search, and secondly, only PS is utilized to fine-search. Experiments on different test functions such as Hump, Powell, Rosenbrock, Schaffer, and Woods demonstrate that this proposed GPS is superior to improved GA and improved PS with respect to successful rate. Accordingly, GPS is an effective and feasible global optimization algorithm.

关 键 词：遗传算法 模式搜索 全局优化 

分 类 号：TN911.73[电子电信—通信与信息系统]