融合历史记忆的单纯形引导鲸鱼优化算法  

Simplex guided whale optimization algorithm integrating historical memory

作　　者：杜晓昕[1] 周薇 王波 王振飞 张剑飞[1] DU Xiao-xin;ZHOU Wei;WANG Bo;WANG Zhen-fei;ZHANG Jian-fei(College of Computer and Control Engineering,Qiqihar University,Heilongjiang Qiqihar 161006,China)

机构地区：[1]齐齐哈尔大学计算机与控制工程学院,黑龙江齐齐哈尔161006

出　　处：《齐齐哈尔大学学报（自然科学版）》2024年第2期40-44,50,共6页Journal of Qiqihar University(Natural Science Edition)

基　　金：黑龙江省省属高等学校基本科研费自然科学类青年基本创新人才项目(145209206)。

摘　　要：针对鲸鱼优化算法存在易陷入局部最优、收敛速度慢等缺点,提出一种融合历史记忆的单纯形引导鲸鱼优化算法。首先,为了避免初始化种群过于集中而陷入局部最优,提出了使用混沌映射对初始化种群进行改进,增加了种群多样性;其次,为了解决算法收敛精度低和收敛速度慢的问题,提出了融合历史记忆的单纯形引导策略,利用单纯形法和构建的历史记忆表求解出一个虚拟最优解作为下次随机搜索阶段的引导者,帮助种群在前期的勘探过程中进行细致地搜索;最后提出一种新的非线性参数策略,平衡算法的开发和勘探能力。将算法应用于12个典型的复杂函数优化问题,并与其他5种智能算法比较,实验结果表明,改进后的算法在收敛精度与速度方面均为第一,具有良好的全局搜索能力和局部开发能力。In view of the shortcomings of whale optimization algorithm,such as easy to fall into local optimum and slow convergence speed,a simplex-guided whale optimization algorithm integrating historical memory was proposed.Firstly,in order to avoid the initial population being too concentrated and falling into the local optimum,the chaotic map was proposed to improve the initialized population and increase the population diversity.Secondly,in order to solve the problems of low convergence accuracy and slow convergence speed of the algorithm,a simplex guidance strategy fused with historical memory was proposed,and a virtual optimal solution was solved by using the simplex method and the constructed historical memory table as the guide in the next random search stage,which helped the population to conduct a more detailed search in the early exploration process.Finally,a new nonlinear parametric strategy is proposed to balance the development and exploration capabilities of the algorithm.The algorithm is applied to 12 typical complex function optimization problems,and compared with other five intelligent algorithms,the experimental results show that the improved algorithm is the first in terms of convergence accuracy and speed,so it can be shown that the algorithm has good global search ability and local development ability.

关 键 词：鲸鱼优化算法 混沌映射 单纯形法 非线性参数 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]