一种改进的多目标粒子群优化算法及其应用  

Improved MOPSO algorithm and its application

作　　者：冯金芝[1,2] 陈兴[1] 郑松林[1,2] 

机构地区：[1]上海理工大学机械工程学院,上海200093 [2]上海理工大学机械工业汽车底盘机械零部件强度与可靠性评价重点实验室,上海200093

出　　处：《计算机应用研究》2014年第3期675-678,683,共5页Application Research of Computers

基　　金：国家"十二五""863"计划重大项目(2011AA11A265;2012AA110701);国家自然科学基金资助项目(50875173);上海市科委科研计划资助项目(11140502000);上海汽车工业科技发展基金资助项目(1104)

摘　　要：为提高多目标粒子群优化(MOPSO)算法处理多目标优化问题的性能,降低计算复杂度,改善算法的收敛性,提出了一种改进的多目标粒子群优化算法。通过运用比例分布及跳数改进机制策略的方法,使该算法不仅继承了MOPSO算法的优点,而且具有很强的局部搜索能力和较好的鲁棒性能,使非劣解集均匀分布,尽可能逼近真实的非劣前沿。通过对多连杆悬架空间结构硬点的多目标优化,进一步验证了该算法的实用性及其优越性。In order to enhance the multi-objective particle swarm optimization （MOPSO） algorithm processing performance for multi-objective optimization, reduce the computational complexity and improve the convergence of algorithm, this paper put for- ward an improved multi-objective particle swarm optimization algorithm, which used proportional distribution and jump improved mechanism, not only inherited the advantages of MOPSO algorithm, but had a strong local searching ability, good robust performance and uniform non-inferior solution set, as far as possible approximation real non-inferior front. The pract!cability and superiority of the proposed algorithm is verified by applying it into multi-objective optimization of the spatial structure geometry pa- rameters of a multi-link suspension.

关 键 词：多目标粒子群优化 比例分布 跳数改进机制 多连杆悬架 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]