摘要
针对黏菌算法(slime mould algorithm,SMA)搜索效率低和陷入局部最优的问题,本文提出一种多策略改进黏菌算法。首先,通过Tent映射反向学习策略求得较优种群作为初始种群,提高算法收敛速度;其次,黏菌通过自适应权值策略和扰动策略更新位置,调整算法勘探能力和开发能力,避免陷入早熟并提高收敛速度;最后,与PSO、WOA、GWO、SMA等4种算法和相关改进SMA算法相比,对CEC测试函数的寻优结果表明:本文改进算法的搜索效率和避免陷入局部最优能力较强,算法能在较短时间内找到全局最优值,对测试函数的收敛速度和收敛精度均有不同程度提高。
Aiming at the problem of low search efficiency and local optimum of Slime Mould Algorithm(SMA),an improved multi-strategy Slime Mould Algorithm is proposed.Firstly,the optimal population is obtained by Tent mapping reverse learning strategy as the initial population to improve the convergence speed of the algorithm.Secondly,slime molds updates location through adaptive weight strategy and disturbance strategy,adjusts the exploration and development ability of the algorithm,avoids falling into premature,and improves the convergence speed.Finally,compared with four classical algorithms including PSO,WOA,GWO,SMA and a related improved SMA algorithm,CEC test function is tested.The optimization results show that the improved algorithm has strong search efficiency and ability to avoid falling into local optimum.The algorithm can find the global optimal value in a short period of time,which are more effective and can improves the convergence speed and convergence accuracy of the test function to some degrees.
作者
王喜敏
袁杰
寇巧媛
WANG Ximin;YUAN Jie;KOU Qiaoyuan(School of Electrical Engineering,Xinjiang University,Urumqi Xinjiang 830017,China)
出处
《广西师范大学学报（自然科学版）》
CAS
北大核心
2022年第6期98-108,共11页
Journal of Guangxi Normal University:Natural Science Edition
基金
国家自然科学基金(61863033,62073227)
新疆维吾尔自治区天山青年计划优秀青年人才培养项目(2019Q018)
新疆维吾尔自治区研究生创新项目(XJ2021G061)。
关键词
TENT映射
反向学习策略
自适应权值策略
扰动策略
黏菌算法
Tent map
reverse learning strategy
adaptive weight strategy
perturbation strategy
slime molds algorithm
