一种多策略融合改进的人工蜂鸟算法  

An Artificial Hummingbird Algorithm Improved by Multi-Strategy Fusion

作　　者：王红旗 张超[1] WANG Hongqi;ZHANG Chao(Department of Computer Information,Suzhou Vocational and Technical College,Suzhou Anhui 234000,China)

机构地区：[1]宿州职业技术学院计算机信息系,安徽宿州234000

出　　处：《信息与电脑》2025年第6期139-143,共5页Information & Computer

基　　金：安徽省高校自然科学重点项目“群体智能优化算法在图像分割中的应用研究”(项目编号:2024AH051831);“求解大规模优化问题的群体智能优化算法研究与应用”(项目编号:2023AH052956)。

摘　　要：针对人工蜂鸟算法全局搜索能力不强、易陷入局部最优的问题,提出了一种多策略融合改进的人工蜂鸟算法(Improved Artificial Hummingbird Algorithm,IAHA)。首先,在引导觅食阶段对最大未访问次数候选食物源的数量进行分类,以提升全局搜索能力;其次,在区域觅食阶段引入Levy飞行及历史最佳位置,以提升跳出局部最优能力;最后,在迁徙觅食阶段增加更新次数表,以提升种群多样性和跳出局部最优能力。在MATLAB2020上进行IAHA和三种对比算法的性能对比实验,测试函数选择CEC2022函数测试集。实验结果表明,IAHA算法性能优于对比算法。In response to the problem of weak global search ability and susceptibility to local optima in the artificial hummingbird algorithm,a multi strategy fusion improved artificial hummingbird algorithm(IAHA)is proposed.Firstly,during the guided foraging phase,classify the maximum number of unvisited candidate food sources to enhance global search capabilities;Secondly,Levy flights and historical best positions are introduced in the regional foraging phase to enhance the ability to jump out of local optima;Finally,increase the update frequency table during the migration and foraging phase to enhance population diversity and escape from local optima.Conduct performance comparison experiments between IAHA and three comparison algorithms on MATLAB 2020,using the CEC2022 function test set as the testing function.The experimental results show that the IAHA algorithm performs better than the compared algorithms.

关 键 词：群体智能优化算法 人工蜂鸟算法 收敛精度 收敛速度 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]