摘要
针对基本粒子群算法存在着收敛速度慢、效率低、易陷入局部最优等缺陷,为了更好地平衡全局和局部搜索能力,在粒子群算法中引入收缩因子,使算法中粒子不仅向种群最优的粒子进行学习,而且向种群中比自己优秀的所有粒子学习,增加了粒子的多样性。实验结果证明,与基本蚁群算法相比,改进的粒子群算法提高了收敛速度和效率,能一定程度地避免局部最优解的产生。
In view of the basic particle swarm optimization algorithm exits the slow speedconvergence,low efficiency,and is easy to fall into the local optimum.In order to better balance theglobal and local search capability,the shrinkage factor is introduced into the particle swarmoptimization algorithm.The particle of the population not only learn from the best particle,but alsolearn from all the particles in the algorithm,the diversity of particles is increased,The experimentalresults show that the improved particle swarm optimization algorithm can improve convergence speedand efficiency,and avoid the generation of local optimal solution comparing with the basic ant colonyalgorithm.
作者
任贺宇
郭磊
赵开新
REN He-yu;GUO Lei;ZHAO Kai-xin(Henan Communication Vocational Technology College,Zhengzhou 450000,China;Henan Provincial Civil Affairs School, Zhengzhou 450002,China;Henan Institute of Technology, Xinxiang 453002,China)
出处
《火力与指挥控制》
CSCD
北大核心
2017年第8期120-122,共3页
Fire Control & Command Control
基金
国家自然科学基金(61174085)
河南省高等学校重点科研基金资助项目(16A520084)
关键词
粒子群
全局最优
局部最优
学习规则
particle swarm
global optimum
local optimum
learning rule
