摘要
针对野马优化算法存在种群多样性低、收敛速度慢和易陷入局部最优等问题,提出一种混合策略改进的野马优化算法(IWHO)。在马驹位置公式中引入基于饥饿游戏的Tent惯性权重,更好平衡算法的全局搜索与局部搜索能力;在放牧阶段引入折射镜像学习策略,利用折射镜像学习生成可行解的反向解,加快算法的求解速度;利用混合黄金正弦与飞蛾扑火算子,使算法跳出局部最优。将改进后的算法(IWHO)和其它算法在10个基准函数上对比测试,并通过Wilcoxon秩和检验和拉/压弹簧设计问题验证算法性能。仿真结果表明,IWHO在收敛速度和寻优精度上有明显改进。
Aiming at the problems of low population diversity,low speed of convergence,and the problem that it is prone to fall into local optimum in wild horse optimizer(IWHO),the Tent inertial weight based on hunger games was introduced into the foals position formula to develop the global search and local search ability of the algorithm to acquire a better balance.Refraction mirror learning strategy was used to generate the reverse solution of the feasible solution and improve the precision of the algorithm in the grazing phase.An operator was used which was mixed by golden sine and moth-flame,the best position of the wild horse was disturbed to make the algorithm to jump out of local optimum.The improved algorithm(IWHO)was compared with other algorithms on 10 benchmark functions,and Wilcoxon and tension/compression string design problem was used to verify its performance.Simulation results show that IWHO has obvious improvement in convergence speed and optimization accuracy.
作者
李姗鸿
靳储蔚
张达敏
张琳娜
LI Shan-hong;JIN Chu-wei;ZHANG Da-min;ZHANG Lin-na(School of Big Data and Information Engineering,Guizhou University,Guiyang 550025,China;School of Mechanical Engineering,Guizhou University,Guiyang 550025,China)
出处
《计算机工程与设计》
北大核心
2024年第2期405-413,共9页
Computer Engineering and Design
基金
国家自然科学基金项目(62062021、61872034)
贵州省科学技术基金项目(黔科合基础[2020]1Y254)。
关键词
野马优化算法
饥饿游戏搜索算法
混沌映射
惯性权重
折射镜像学习
函数优化
收敛曲线
wild horse optimizer
hunger games search
chaotic mapping
inertia weight
refraction mirror learning
function optimization
convergence curve
