带黑洞机制和混沌搜索的多目标粒子群算法  

Multi-objective Particle Swarm Optimization with Black Hole Mechanism and Chaotic Search

作　　者：夏禹[1,2] 吴朋 XIA Yu;WU Peng(School of Automation Chongqing University, Chongqing 400000, China;Chongqing Chuanyi Automation Co., Ltd. Chongqing 400000, China)

机构地区：[1]重庆大学自动化学院,重庆400000 [2]重庆川仪自动化股份有限公司,重庆400000

出　　处：《控制工程》2019年第2期251-257,共7页Control Engineering of China

基　　金：国家2015年战略性新兴产业发展专项资金

摘　　要：多目标粒子群优化算法(Multiobjectiveparticleswarmoptimizationalgorithm,MOPSO)在算法后期容易陷入局部最优,为了防止算法"早熟",提出了带黑洞机制和混沌搜索的多目标粒子群优化算法。他利用随机黑洞机制,对领导粒子周围进行搜索;利用混沌运动遍历性的特点,使得粒子在个体最优点附近的搜索区域增大,从而增加种群的多样性,防止陷入局部最优。通过改进后的ZDT系列函数验证,表明了算法能解决2维空间下的高维解问题,通过DTLZ系列函数验证,表明了算法也能有效解决3维目标问题。MOPSO is easy to fall into local optimum in the late stage of the algorithm, in order to prevent the "premature", the multi objective particle swarm optimization algorithm with black hole mechanism and chaotic search is proposed. The random black hole mechanism is adopted to search around the lead particle. By characteristics of chaos ergodicity, the search area around individual optimal point has expanded, so as to increase the diversity of the population and prevent falling into local optimum. The solution of improved ZDT series functions show that the algorithm can solve the problem of high dimensional solutions in 2-dimensional space, and the solution of the improved DTLZ series functions show that the algorithm can effectively solve the3-dimensional space.

关 键 词：黑洞机制 混沌搜索 多目标 粒子群优化 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]