基于自适应权重和动态螺旋参数的鲸鱼算法  

Whale Optimization Algorithm Based on Adaptive Weights and Dynamic Spiral Parameters

作　　者：郭岩 李目[1] 徐佳祺 王奕峰 雷佳伟 GUO Yan;LI Mu;XU Jiaqi;WANG Yifeng;LEI Jiawei(School of Information and Electrical Engineering,Hunan University of Science and Technology,Xiangtan 411201,China)

机构地区：[1]湖南科技大学信息与电气工程学院,湖南湘潭411201

出　　处：《湖南科技大学学报(自然科学版)》2025年第1期78-87,共10页Journal of Hunan University of Science And Technology:Natural Science Edition

基　　金：国家自然科学基金资助项目(61404049);湖南省自然科学基金资助项目(2020JJ6031);湖南省教育厅重点项目资助(22A0324);湖南省教育厅优秀青年基金资助项目(17B094);湘潭市创建国家创新型城市建设专项项目资助(NY-YB20221042)。

摘　　要：针对鲸鱼优化算法(Whale Optimization Algorithm, WOA)收敛性能差,易陷入局部最优值的问题,提出一种基于自适应权重和动态螺旋参数的鲸鱼优化算法(ADS-WOA).首先,引进一种非线性距离控制因子,提高算法的开发勘探能力;其次,提出一种自适应惯性权重,提高算法后期的收敛速度;最后,改进WOA的螺旋形状参数,改变鲸鱼种群固定的螺旋上升路径,提高算法的收敛精度和收敛速度.将ADS-WOA和其他优化算法在10组基准测试函数上进行测试,并对测试结果进行Wilcoxon秩和检验,以及对3种改进策略和ADS-WOA时间复杂度的分析.结果表明:ADS-WOA算法具有更好的寻优和抗干扰能力,能够应用于高维复杂环境下的目标函数优化问题.Aiming at the poor convergence performance of whale optimization algorithm(WOA)and the problem of local optimization,a whale optimization algorithm(ADS-WOA)based on adaptive weights and dynamic spiral parameters is proposed.First of all,a nonlinear distance control factor is introduced to improve the exploitation and exploration ability of the algorithm.Secondly,an adaptive inertia weight is proposed to improve the convergence speed of the algorithm in the later stage.Finally,the spiral shape parameters of WOA are improved,the fixed spiral path of whale populations is changed,and the convergence accuracy and convergence speed of the algorithm are improved.ADS-WOA and other optimization algorithms are tested on 10 sets of benchmark functions,and the test results are tested with Wilcoxon rank sum test,as well as an analysis of three improvement strategies and ADS-WOA time complexity.The results show that compared with WOA,ADS-WOA algorithm has better optimization and anti-interference capabilities,and can cope with objective function optimization problems in high-dimensional complex environments.

关 键 词：鲸鱼优化算法 距离控制因子 惯性权重 Wilcoxon秩和检验 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]