基于遗传算法和灰色关联度的多目标问题求解方法研讨.pdfVIP

th Proceedings of the 25 Chinese Control Conference 7-11 August, 2006, Harbin, Heilongjiang 基于遗传算法和灰色关联度的多目标问题求解方法研究 1 1,2 李俊峰 , 戴文战 1. 浙江理工大学 自动化系, 杭州 310018 E-mail: ljf2003zz@163.com 2. 浙江工商大学信息与电子工程学院, 杭州 310035 E-mail: dwzhan@ 摘 要: 本文基于自适应遗传算法和灰色关联度提出了一种新的求解多目标问题非劣解的方法. 首先分别求出多 目标中每个单目标的最优解, 以该最优解向量为参考向量, 求各个个体与参考向量的灰色关联度, 并以该关联度 为个体适应度, 用遗传算法求解多目标问题的非劣解, 自适应交叉和变异概率可以控制非劣解替换和保持种群多 样性. 最后用实例验证了本文方法的有效性. 关键词: 自适应遗传算法, 多目标问题, 灰色关联度 Research of Solving Method against Multi-objective Problem Based on Adaptive Genetic Algorithm and Grey Relation Degree Li Junfeng 1 , Dai Wenzhan1.2 1. Department of Automatic control, Zhejiang Sci-Tech University, Hangzhou 310018, China E-mail: ljf2003zz@163.com 2. College of Information and Electronic Engineering ，Zhejiang Gongshang University, Hangzhou 310033, China E-mail: dwzhan@ Abstract: In this paper, based on adaptive genetic algorithm and grey relation degree, a new method for solving multi-objective problem is put forward. First, the best solution of every objective in the middle of the multi-objective is solved and they are looked on as referenced vector. Second, the grey relation degree between every individual and the referenced vector is solved and the grey relation degree is acted as fitness of the individual. At last, the pareto optimal sets are solved by means of adaptive genetic algorithm. The variety of population is kept