一种基于非线性惯性权重的海鸥优化算法  

Seagull Optimization Algorithm Based on Nonlinear Inertia Weight

作　　者：秦维娜 张达敏 尹德鑫 蔡朋宸 QIN Wei-na;ZHANG Da-min;YIN De-xin;CAI Peng-chen(College of Big Data and Information Engineering,Guizhou University,Guiyang 550025,China)

机构地区：[1]贵州大学大数据与信息工程学院,贵阳550025

出　　处：《小型微型计算机系统》2022年第1期10-14,共5页Journal of Chinese Computer Systems

基　　金：贵州省科学技术基金项目(黔科合基础[2020]1Y254)资助。

摘　　要：针对海鸥算法(SOA)在求解最优化问题中的不足和算法性能依赖于参数的选取等缺点,提出一种基于惯性权重的海鸥优化算法(Inertia Seagull optimization algorithm, I-SOA),采用非线性递减的惯性权重计算附加变量A的值来调整的海鸥的位置,通过莱维飞行和随机指数值增加海鸥飞行的随机性,增强算法搜索寻优的全局能力,避免算法寻优搜索陷入局部优值;通过12个基准测试函数将I-SOA与标准PSO,SOA,GA算法进行测试比较.实验对比结果表明,所提出的I-SOA优化算法具有较快的收敛速度、较高的求解精度和全局收敛能力.Seagulls algorithm(SOA) insufficient in solving optimization problem and algorithm performance depends on the selection of parameters such as faults, presents A Seagull optimization algorithm based on Inertia weight(Inertia Seagull optimization algorithm, I-SOA),using nonlinear decreasing Inertia weight calculation of additional variable A value to adjust the position of the gulls, through A levy flight and random index value increase the randomness of seagulls enhancement algorithm search optimization ability of global, avoid optimization search algorithm trapped in local optimal value;Twelve benchmark functions were used to test I-SOA against standard PSO,SOA and GA algorithms.Experimental results show that the proposed I-SOA optimization algorithm has fast convergence speed, high solution accuracy and global convergence ability.

关 键 词：海鸥优化算法 莱维飞行 全局寻优 惯性权重 函数优化 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]