混合多项自适应权重的混沌麻雀搜索算法  

Chaotic Sparrow Search Algorithm with Mixed Multinomial Adaptive Weights

作　　者：杜云 周志奇 贾科进 丁力 卢孟杨林 DU Yun;ZHOU Zhiqi;JIA Kejin;DING Li;LU Mengyanglin(College of Electrical Engineering,Hebei University of Science and Technology,Shijiazhuang 050031,China)

机构地区：[1]河北科技大学电气工程学院,石家庄050031

出　　处：《计算机工程与应用》2024年第7期70-83,共14页Computer Engineering and Applications

基　　金：河北省重点研发计划项目(21375801D,19221814D)。

摘　　要：麻雀搜索算法具有原理简单、搜索能力强、快速寻优等优点,但是存在全局搜索不足、易陷入局部最优等缺点,针对其缺点提出了混合多项自适应权重的混沌麻雀搜索算法。增加改进Circle混沌映射提高种群多样性;在发现者引入自适应权重策略,提高发现者的全局搜索能力和搜索范围;在加入者引入改进鲸鱼优化算法的气泡网捕食策略,提高算法的局部搜索性能和跳出局部最优的能力;结合反向学习策略机制,对所有的个体进行最优选择,使每次迭代后的个体质量得到提升,以提高算法的寻优效率和寻优精度。将混合多项自适应权重的混沌麻雀搜索算法与4种经典基本算法和9种改进的麻雀搜索算法在12种测试函数和CEC2022测试函数上进行对比,改进算法有更好的寻优性能和收敛速度。Sparrow search algorithm has the advantages of simple principle,strong search ability and fast optimization search,but there are shortcomings such as insufficient global search and being easy to fall into local optimization,etc.The paper proposes a chaotic sparrow search algorithm with mixed multinomial adaptive weights to deal with its shortcomings.Improved Circle chaotic mapping is added to improve the diversity of the population;an adaptive weighting strategy is introduced in the explorer to improve the global search ability and expand the search range of the explorer;bubble net predation strategy is introduced in the joiner to improve the whale optimization algorithm,which improves the local search performance of the algorithm and the ability to escape local optima;and combined with the mechanism of the backward learning strategy,the optimal selection of all individuals is made to improve the quality of individuals in each iteration,thereby improving the quality of the algorithm.The quality of individuals is improved to enhance the algorithm's optimization search efficiency and accuracy.The chaotic sparrow search algorithm with mixed multinomial adaptive weights is compared with four classical baseline algorithms and nine improved sparrow search algorithms on 12 benchmark functions and CEC2022 problems,and the improved algorithms in the paper demonstrate better optimization performance and faster convergence speed.

关 键 词：麻雀搜索算法 Circle混沌映射 自适应权重 鲸鱼优化算法 反向学习 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]