模糊理论在遗传算法中的运用  

THE APPLICATION OF FUZZY THEORY TO GENETIC ALGORITHMS

作　　者：胡小兵[1] 吴树范[1] 江驹[1] 

机构地区：[1]南京航空航天大学自动化学院,南京210016

出　　处：《模式识别与人工智能》2001年第1期109-113,共5页Pattern Recognition and Artificial Intelligence

摘　　要：遗传算法的寻优能力和收敛速度与许多因素有关,其间的关系复杂且难以精确描述。模糊理论能很好地描述这种特性。本文分析了影响遗传算法寻优能力和收敛速度的多种因素,运用模糊理论指导遗传算法中交叉和变异概率的自适应调整,以及改善局部寻优能力。实验结果表明,此法是有效可行的。The optimizing capability and convergence speed of a genetic algorithm are related to many factors, and their relations are complex and hard to be described. Fuzzy theory can describe such complex problems well. In this paper, some factors affecting the performance of genetic algorithms are analyzed. Then fuzzy theory is used to instruct the self-adapting adjustment of crossover and mutation probability, and to strengthen local optimizing capability. And experiment results show such idea is effective and feasible.

关 键 词：遗传算法模糊理论 寻优 收敛 自适应 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]