一种自适应的遗传算法  

An adaptive genetic algorithm

作　　者：段宏斌[1] 韩琳[2] 

机构地区：[1]杨凌职业技术学院 [2]西安工程科技学院理学院

出　　处：《纺织高校基础科学学报》2006年第1期80-84,共5页Basic Sciences Journal of Textile Universities

摘　　要：针对基本遗传算法的稳定性较差、存在未成熟收敛和易陷入局部最优解的问题,提出一种基于交叉概率和变异概率的自适应遗传算法.该算法通过将交叉概率和变异概率随适应度自动改变,实现有目标地对不同个体进行交叉和变异操作,以达到快速扩大搜索空间、稳定群体中个体多样性的目的.仿真结果表明,该算法的收敛性能优于基本遗传算法,有效地避免了基本遗传算法中因选择压力过大造成未成熟收敛现象,显著提高了遗传算法对全局最优解的搜索能力和收敛速度.According to the porblems of the simple genetic algorithm＇s weak stable property, the premature convergene and easily getting into local optimum ,a new adaptive genetic algorithm is presented which is based on the crossover probability and mutation probability. In order to enlarge the search space rapidly and keep the variety of population at a stable level, through changing crossover probability and mutation probability automatically with fitness, the crossover and mutation operation are used on different individual purposefully, The simulation experiments show that this algorithm has great advantage of convergence property over simple genetic algorithm, and it can effectively avoid the premature convergence problem caused by the high selective pressure in simple genetic algorithm. Moreover, the algorithm improves the ability of searching an optimum solution and increases the convergent speed.

关 键 词：自适应遗传算法 交叉概率 变异概率 未成熟收敛 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]