遗传算法中选择交叉策略的改进  

Improvement of Selection and Crossover Strategy in Genetic Algorithm

作　　者：冯冬青[1] 王非[1] 马雁[1] 

机构地区：[1]郑州大学电气工程学院,郑州450001

出　　处：《计算机工程》2008年第19期189-191,共3页Computer Engineering

基　　金：河南省自然科学基金资助项目(0511010800)

摘　　要：提出一种改进的遗传算法,为排序选择压力引入自适应调节机制,确保选择压力随种群性状的改变而动态调整,采用新的竞争择优交叉策略提高种群中个体的平均性能。选取典型测试函数进行仿真,结果表明该算法在寻优精度和收敛速度上较原有算法均有较大提高,收敛概率达90%以上。This paper proposes an improved Genetic Algorithm（GA）. The ranking selection intensity adopts an adaptive adjusting mechanism, which can adjust the selection intensity dynamically according to the change of the population state. A new crossover strategy which chooses the outstanding individuals according to competition is used to increase the individual average performance of the population. The simulation with the typical test functions indicates that tl^is algorithm can improve the precision of solutions and convergence speed of simple genetic algorithm, and the proportion of convergence can reach more than 90%.

关 键 词：遗传算法 排序选择 交叉策略 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]