摘要
针对遗传算法中的早熟收敛现象,提出了一种改进的遗传算法.该算法利用种群多样性算子产生较好的初始种群分布,并以该算子作为判断种群是否早熟收敛的依据.一旦出现早熟收敛或早熟收敛的趋势,则进行灾变,以恢复算法的进化能力.同时结合种群的最优个体和引入的随机种群,设计了一种包含选择、交叉算子的一般性算子,使算法能有效维持种群的多样性,快速找到全局最优解.
An improved genetic algorithm is proposed to overcome premature convergence of the genetic algorithm. This improved algorithm uses a population diversity operator to initidlizé population with better distribution and to judge whether premature convergence occurs. Once premature convergence appears or tends to appear, the catastrophe operation is implemented to renew the population evolution of the algorithm. At the same time, a universal operator with selection and crossover operator is designed in combination with optimum individual and introduced random population in order to make the proposed algorithm＇s ability of maintaining population diversity and finding overall optimum solution. Experiments with four test functions demonstrate that the improved genetic algorithm can effectively maintain population diversity and prevent premature convergence.
出处
《西南大学学报（自然科学版）》
CAS
CSCD
北大核心
2008年第1期156-159,共4页
Journal of Southwest University(Natural Science Edition)
基金
西南师范大学发展基金资助项目(SWNUF2004006)
重庆市自然科学基金资助项目(2007BB2331)
关键词
早熟收敛
遗传算法
种群多样性
测试函数
premature convergence
genetic algorithm
population diversity
test function
