摘要
利用遗传算法对具有多个极值点的目标问题进行优化时,往往会发生早熟现象,针对这一问题,提出一种基于密度调节的遗传算法,将每代个体按照目标函数均值进行分组,对优良个体进行海明距离检测,淘汰相似个体,保证种群多样性。通过仿真把该算法和SGA进行比较,证明了该算法的有效性。
In order to handle the premature convergence problems when using genetic algorithm to solve the functions with multiple extreme point, the paper puts forward an improved genetic algorithm based on density regulation, each generation of individuals are grouped according to the objective function value, every better individual is tested according to the Hamming distance, and remove the similar individual, to ensure diversity of population. Comparing the algorithm with SGA through simulation, which proves the algorithm’s effectiveness.
出处
《微计算机信息》
2010年第27期208-209,200,共3页
Control & Automation
基金
运城学院院级项目
关键词
密度调节
早熟
海明距离
遗传算法
density regulation
premature convergence
Hamming distance
genetic algorithm
