摘要
提出了一种基于优良个体特征模式的方向变异(DM)算子以改进标准遗传算法的随机变异,它不仅能提高种群的多样性,增强其在解空间的搜索能力,也能提高遗传算法的收敛速度.在对多峰值函数的优化时,将该算法和标准遗传算法结果比较,表明该算法有良好的稳定性.
This paper proposes a new direction - mutation (DM) method based on better individual, which replace the random mutation in SGA (standard genetic algorithm). This algorithm can not only improve the speed of convergence, but also enlarge the multifamily of the population, so the optimizing resolution can be obtained in global. According to the result of test, the algorithm has been proved that it is more effective and more feasible than the SGA.
出处
《上海师范大学学报（自然科学版）》
2004年第3期43-47,共5页
Journal of Shanghai Normal University(Natural Sciences)
关键词
遗传算法
多峰值函数
适应度
小生境
分段海明距离
genetic algorithm
multi-peak-value
adaptability
optimizing resolution
nicked segment-hamming
