中文摘要：

针对遗传算法容易过早地收敛于局部最优解,即早熟问题,本文分析了产生早熟问题的原因,并在此基础上提出了个体相似度的概念。通过个体相似度选择进行交叉操作的父代个体,同时给出一种新的自适应调整交叉概率和变异概率的策略,并以求Schaffer’s F6函数的最大值为目标进行仿真实验。仿真结果表明,改进遗传算法跳出局部最优值的能力大于标准遗传算法和文献[12]算法,平均函数值也高于两者。因此,在全局收敛性上,该方法要优于标准遗传算法和传统自适应遗传算法,能够有效地避免早熟问题的发生。该研究适合于实际的工程应用。

英文摘要：

The genetic algorithm is easy to converge to the local optimal solution,that is,premature problem.The causes of premature problem are analyzed in this paper.And based on the analysis,the concept of individual similarity is put forward.The parent individuals of cross operation are selected by the individual similarity.At the same time,a new strategy for adaptive adjustment of crossover probability and mutation probability is presented.And the simulation experiment is carried out in to find the maximum value of Schaffer＇s F6 function.The simulation results show that the improved genetic algorithm in this paper is better than the standard genetic algorithm and the genetic algorithm in literature [12]on the ability to jump out of the local optimal value.And the average function value of the improved genetic algorithm in this paper is also higher than the standard genetic algorithm and the genetic algorithm in literature[12].Thus,the proposed method is superior to the standard genetic algorithm and the traditional adaptive genetic algorithm in global convergence aspect.It can effectively avoid the occurrence of premature problem.This study is suitable for practical engineering applications.