摘要
采用大规模种群进化优化策略,根据用户评价时间和单一数值适应值估计个体模糊适应值;根据个体表现型属性和参照个体模糊适应值宽度计算个体表现型相似度;利用个体表现型相似度对种群聚类并估计未评价个体的模糊适应值;基于个体模糊适应值和表现型相似性构造个体选择适应值,实现个体相似性选择.将所提出方法应用于室内挂钟进化设计,并与已有典型方法进行比较.结果表明,所提出方法在提高优化质量、减轻用户疲劳、提高搜索效率等方面均具有优越性.
Individuals＇ fuzzy fitness is estimated according to user＇s evaluation time and single numerical fitness by using the large-scale population evolutionary optimization strategy. Individual phenotype similarity is calculated according to the individuals＇ phenotype attributes and the width of individuals＇ fuzzy finess. The population is divided into several clusters and the not assigned individuals＇ fuzzy fitness is estimated by using individuals＇ phenotypes similarity. The individuals＇ choice fitness is constructed based on individuals＇ fuzzy fitness and phenotype similarity to achieve individual similarity selection. The proposed algorithm is applied to a wall clock evolutionary design system, and compared with existing typical ones.The experimental results show that the proposed algorithm has advantages in improving optimization quality and alleviating user fatigue while improving its efficiency in exploration.
作者
郭广颂
陈良骥
文振华
侯军兴
GUO Guang-song;CHEN Liang-ji;WEN Zhen-hua;HOU Jun-xing(School of Mechatronics Engineering,Zhengzhou University of Aeronautics,Zhengzhou 450046,China;School of Mechanical Engineering,Tianjin Polytechnic University,Tianjin 300387,China)
出处
《控制与决策》
EI
CSCD
北大核心
2018年第9期1559-1566,共8页
Control and Decision
基金
国家自然科学基金项目(61673196)
河南省科技攻关项目(172102210513)
河南省高等学校重点科研项目(18A120012)
关键词
遗传算法
交互
估计
模糊适应值
相似度
genetic algorithms
interaction
estimation
fuzzy fitness
similarity
