摘要
为了克服标准遗传算法的早熟现象 ,提高遗传算法的全局收敛性 ,提出了一种基于基因重组策略的遗传算法 .该算法定义了一种新的交叉算子 ,即移位逻辑交叉算子 (包括蝶形移位交叉算子和洗牌移位交叉算子 ) ,用它们对染色体的部分基因实现有规律的交叉重组 .实验结果表明 ,该算法比经典的遗传算法具有更好的收敛性和稳定性 .
To overcome the drawback of prematurity in classical GA and improve its global convergency, this paper presens a new type of genetic algorithm which is based on the parallel strategy of gene reconfiguration. The algorithm uses a new type of cross operators called shift logical cross operation which includes butterflying and shuffling logical cross operation. These cross operations reconfigure a part of genes in the chromosome according to a special rule. Experimental results show that the method has much higher convergence speed and stability than classical GA.
出处
《扬州大学学报（自然科学版）》
CAS
CSCD
2003年第1期46-51,共6页
Journal of Yangzhou University：Natural Science Edition
基金
国家自然科学基金资助项目 (6 0 0 74 0 13)
国家高性能计算基金资助项目 (992 10 )
江苏省教育厅自然科学基金资助项目 (99KJB5 2 0 0 0 3)
