一种快速实现多峰值函数优化的改进遗传算法  

An Improved Genetic Algorithm of Fast Realization in Multimodal Function Optimizations

作　　者：盛鹰[1] 易丽清[1] 魏泳涛[1] 

机构地区：[1]四川大学建筑与环境学院,四川成都610065

出　　处：《西南科技大学学报》2009年第2期82-87,共6页Journal of Southwest University of Science and Technology

摘　　要：针对基本遗传算法具有的收敛早熟、局部搜索能力差等缺点,提出了一种快速实现多峰值函数优化的改进算法。该算法包含并行小生境技术、可疑峰值点判断、引入局部搜索参数等策略,并采用C语言成功编写了通用程序。数值算例表明:该改进算法能有效防止早熟收敛,明显提高遗传算法的收敛效率,快速搜索到目标函数的所有最优点。该算法对求解多峰值函数优化问题具有普适性。Considering the disadvantages of simple genetic algorithm （SGA）, such as premature convergence, weakness in local search, etc. , an improved genetic algorithm was proposed in this paper and could fast solve the optimization problem of the function which has much more peaks. Many methods such as parallel niche technique, judgement of possible peak points and introduction of local searching parameters were included in the improved algorithm, and were successfully performed by programming with C language. Numerical examples demonstrated that the improved algorithm can avoid premature effectively,improve the convergence efficiency and fast reach all the global optimal points of the objective function. It has extensive applicability in solving the other multimodal function optimizations.

关 键 词：改进遗传算法 多峰值函数优化 并行小生境技术 局部搜索参数 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构] TP18[自动化与计算机技术—计算机科学与技术]