基于粒子群算法策略改进的飞鼠优化算法  

An Improved Squirrel Search Algorithm Based on Particle Swarm Optimization Strategy

作　　者：朱群锋 王璐[1] 汪超[1] ZHU Qunfeng;WANG Lu;WANG Chao(Anhui University of Technology,Maanshan 243002,China)

机构地区：[1]安徽工业大学机械工程学院,安徽马鞍山243002

出　　处：《洛阳理工学院学报（自然科学版）》2020年第4期52-58,共7页Journal of Luoyang Institute of Science and Technology：Natural Science Edition

基　　金：安徽教育厅科学研究项目(KJ2019ZD09).

摘　　要：为提升飞鼠优化算法的密集搜索能力和收敛速度,提出一种基于粒子群算法策略改进的飞鼠优化算法。受粒子群算法策略的启发,引入惯性权重和学习因子,设计了一种新的飞鼠个体位置更新公式,可以实现飞鼠优化算法在全局探索和局部开发之间的平衡,加快了算法的收敛速度。同时为了抑制飞鼠优化算法的过早收敛,引入概率判断函数,提高了算法的密集搜索能力。该改进算法经过12个基准函数测试,并与其他5个智能优化算法结果进行了对比,在平均收敛值、收敛方差和收敛速度方面显示了该改进算法的有效性与优越性。Based on the recently proposed squirrel search algorithm, in order to improve the intensive search ability and convergence speed of the algorithm, an improved squirrel search algorithm based on particle swarm optimization strategy is proposed. Inspired by the strategy of particle swarm optimization, a new formula of individual position updating is designed by introducing inertia weight and learning factor, which can realize the balance between global exploration and local development, and accelerate the convergence speed of the algorithm. At the same time, in order to restrain the premature convergence of the algorithm, the probability judgment function is introduced to improve the intensive search ability of the algorithm. The improved algorithm is tested by 12 benchmark functions and compared with the results of other five intelligent optimization algorithms. The effectiveness and superiority of the improved algorithm are shown in terms of average convergence value, convergence variance and convergence speed.

关 键 词：飞鼠优化算法 粒子群算法 学习因子 概率判断函数 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]