摘要： 选取粗粒度遗传算法,并针对其过早收敛、收敛速度慢的缺陷进行改进,提出混合粗粒度遗传算法。混合粗粒度遗传算法按照适应度函数值对染色体群体进行分组,各分组采用不同的惩罚系数、交叉、变异算子;同时采用同种互斥和最优解保留策略。实验结果表明该算法在约束最优化问题中应用良好。

关键词: 粗粒度遗传算法, 约束, 最优化问题

Abstract: In this paper, a hybrid coarse-grained genetic algorithm(HCGGA) is proposed to solve the problems of premature convergence and the slow convergence rate of coarse-grained genetic algorithm(CGGA). All chromosomes are ranked according to their fitness values and divided into several subgroups in HCGGA. Each subgroup, whose values of punishment coefficient, crossover and mutation operators are different from other subgroups, operates independently. Otherwise the strategies of the same exclude and the best live are adopted. Experimental result shows that HCGGA is efficient in constrained optimal problems.

中图分类号: 

• TP18