基于S型函数的自适应粒子群优化算法  

S-shaped Function Based Adaptive Particle Swarm Optimization Algorithm

作　　者：黄洋[1] 鲁海燕[1,2] 许凯波 胡士娟 HUANG Yang;LU Hai-yan;XU Kai-bo;HU Shi-juan(School of Science,Jiangnan University,Wuxi,Jiangsu 214122,China;Wuxi Engineering Technology Research Center for Biological Computing,Wuxi,Jiangsu 214122,China)

机构地区：[1]江南大学理学院,江苏无锡214122 [2]无锡市生物计算工程技术研究中心,江苏无锡214122

出　　处：《计算机科学》2019年第1期245-250,共6页Computer Science

基　　金：国家自然科学基金项目(61772013;61402201);中央高校基本科研业务费专项资金项目(114205020513526)资助

摘　　要：针对粒子群算法求解精度低和后期收敛速度慢等问题,提出了一种基于S型函数的自适应粒子群优化算法SAPSO (S-shaped function based Adaptive Particle Swarm Optimization)。该算法利用倒S型函数的特点,实现了对惯性权重的非线性调整,从而更好地平衡算法的全局搜索能力和局部搜索能力;同时,在算法的位置更新公式中引入S型函数,并利用个体粒子自身的适应度值与群体平均适应度值的比值自适应地调整搜索步长,从而提高算法的搜索效率。在若干经典测试函数上的仿真实验结果表明,与已有的几种改进粒子群算法相比,SAPSO在收敛速度和求解精度方面均有较大优势。Aiming at the problems of low solution precision and slow convergence speed in the later stage of particle swarm optimization algorithm,this paper presented an S-shaped function based adaptive particle swarm optimization algorithm(SAPSO).This algorithm takes advantage of the characteristics of upside-down S-shaped function to adjust the inertia weight nonlinearly,better balancing the global search ability and local search ability.In addition,an S-shape function is introduced into the position updating equation,and the ratio of the individual particle’s fitness value to the swarm’s average fitness value is used to adaptively adjust the step size in the search,thus enhancing the efficiency of the algorithm.Simulation results on a set of typical test functions show that SAPSO is superior to several existing improved PSO algorithms significantly in terms of the convergence rate and solution accuracy.

关 键 词：S型函数 惯性权重 位置更新 粒子群优化算法 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]