点击次数：

论文类型：会议论文

发表时间：2018-01-01

收录刊物：CPCI-S

页面范围：39-46

摘要：The design of effective evolutionary many-objective optimization algorithms is challenging for the difficulties in obtaining proximity while maintaining diversity. In this paper, a fast Clustering based Algorithm with reference point Redistribution (fastCAR) is proposed. In the clustering process, a fast Pareto dominance based clustering mechanism is proposed to increase the evolution selection pressure that acts as a selection operator. In the redistribution process, the reference vectors are periodically redistributed by using an SVM classifier to maintain the diversity of the population without extra burden on fitness evaluations. The experimental results show that the proposed algorithm fastCAR obtains competitive results on box-constrained CEC'2018 many-objective benchmark functions in comparison with 8 state-of-the-art algorithms.