基于爬山算子和适应值共享的改进遗传算法  

An Improved Genetic Algorithm Based on Mountain-climbing Operators and Fitness Sharing

作　　者：涂井先[1] 刘伟[1] 

机构地区：[1]广东工业大学应用数学学院,广东广州510006

出　　处：《广东工业大学学报》2011年第1期78-81,共4页Journal of Guangdong University of Technology

摘　　要：提出了一种基于爬山算子和适应值共享的改进遗传算法,将局部搜索算法与遗传算法有效结合,增强了遗传算法的搜索能力.爬山算子以黄金分割法为基础,依次对个体每一维进行优化.数值实验证明,改进后的新算法优于当前一些较好的遗传算法.新算法既有较快的收敛速度,又能以较大概率搜索到优化问题的全局最优解.An improved genetic algorithm,based on mountain-climbing operators and fitness sharing,is proposed.It combines the genetic algorithm with the local searching algorithm effectively,which enhances the searching ability of the genetic algorithm.The mountain-climbing operator,based on the method of golden section,optimizes each dimension of the individual in turn.The results show that the improved algorithm is better than some current algorithms.The new algorithm not only has a rather high convergence speed,but also locates the global optimum with a rather large probability.

关 键 词：遗传算法 适应值共享 爬山算子 黄金分割法 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]