论文部分内容阅读
提出一种解决早熟收敛问题的改进遗传算法.通过最小生成树聚类将种群划分为若干个子种群,子种群内的个体之间及不同子种群间的个体之间同时进行遗传操作.同子种群间个体的遗传操作可以保证算法的进化方向和收敛速度,不同子种群间个体的遗传操作可以避免近亲繁殖,提供多样性.分别采用二进制和实数编码,在经典的23个基准函数上的对比测试结果表明,所提出算法具有较好的收敛速度和寻优能力.
This paper proposes an improved genetic algorithm to solve the problem of premature convergence by dividing the population into several subpopulations by means of minimum spanning tree clustering. The individuals in subpopulations and the individuals in different subpopulations simultaneously perform genetic operations. Genetic operation between individuals can ensure the evolutionary direction and convergence speed of the algorithm, and genetic operation among individuals in different sub-populations can avoid inbreeding and provide diversity.Comparative tests on 23 classic benchmark functions using binary and real codes, respectively The results show that the proposed algorithm has better convergence speed and optimization ability.