摘要
提出一种基于距离测度的实数编码自适应遗传退火算法,根据个体的距离密集度自适应地确定其交叉概率和变异概率.空间距离密集度越高的个体,其交叉概率和变异概率也越高.算法引入模拟退火机制,在遗传进化过程中的每一代,对最优个体进行邻域局部寻优,利用模拟退火进一步改善算法的收敛性能.对带边界约束函数优化问题进行了仿真计算,结果表明该算法有效.
A real-coded adaptive genetic annealing algorithm based on distance measurement is proposed in this paper and the probabilities of crossover and mutation are adaptively determined according to the distance density of chromosomes. Chromosomes with high space distance density have high crossover and mutation probabilities. Simulated annealing mechanism is introduced to do local-search for the best chromosome in every generation of the evolution process. This improves the convergence of the algorithm. This algorithm is used to solve function optimization problem with boundary constraints and computation results show that the algorithm is very effective.
出处
《深圳大学学报（理工版）》
EI
CAS
2004年第4期291-294,共4页
Journal of Shenzhen University(Science and Engineering)
关键词
遗传算法
模拟退火算法
自适应
genetic algorithm
simulated annealing algorithm
adaptive
