动态邻居维度学习的多目标粒子群算法  

Multi-objective particle swarm optimization based on dynamic neigh-borhood for dimensional learning

作　　者：肖闪丽 王宇嘉[1] 聂善坤 XIAO Shanli;WANG Yujia;NIE Shankun(School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China)

机构地区：[1]上海工程技术大学电子电气工程学院,上海201620

出　　处：《计算机工程与应用》2017年第20期31-37,60,共8页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61403249);上海工程技术大学研究生科研创新项目(No.E309031601178)

摘　　要：针对多目标粒子群算法多样性较差,种群选择压力随着变量维度增加的问题,提出了基于动态邻居维度学习的多目标粒子群算法(DNDL-MOPSO)。该算法首先构建最优维度个体,然后在"个体认知"和"社会认知"的基础上,对粒子速度更新公式进行改进,采用每一维上学习对象不固定的交流方式,最后利用随机向导学习策略,增加种群多样性。实验结果表明该方法能够提高算法的全局收敛性,增加种群的多样性,缓解选择压力,有效解决多峰多目标优化问题。Focus on the poor behavior of the diversity for multi-objective particle swarm optimization and the selectionpressure of population increasing with the variable dimension,a Multi-Objective Particle Swarm Optimization based onDynamic Neighborhood of Dimensional Learning(DNDL-MOPSO)is proposed.Firstly,an optimum dimensional individualis established.Then based on the individual and social knowledge,the proposed algorithm improves the formula ofthe velocity updating and uses a strategy that each dimensional learning object is not fixed.Finally,the random guidelearning strategy is used to alleviate the selection pressure.The experimental results indicate that the new algorithm canimprove the global convergence and increase the diversity of population.It is effective to solve the benchmark multimodaloptimization problems.

关 键 词：粒子群算法 多目标优化 动态邻居 最优维度粒子 随机向导学习 

分 类 号：TP202[自动化与计算机技术—检测技术与自动化装置]