混合引力搜索的自适应反向学习蜉蝣优化算法  

Mayfly Optimization Algorithm with Adaptive Opposition Learning and Hybrid Gravitational Search

作　　者：童林 吴芸[1] 吴雪颜 吴霄 江佳玉 TONG Lin;WU Yun;WU Xueyan;WU Xiao;JIANG Jiayu(College of Science,Jiujiang University,Jiujiang 332005,China)

机构地区：[1]九江学院理学院,江西九江332005

出　　处：《广东石油化工学院学报》2023年第1期43-47,51,共6页Journal of Guangdong University of Petrochemical Technology

基　　金：江西省自然科学基金(20224BAB201010);江西省教育厅科技项目(GJJ211823,GJJ211825);江西省大学生创新创业训练计划项目(S202111843039);九江学院大学生创新创业训练计划项目(X202111843144,X202211843019)。

摘　　要：针对蜉蝣优化算法全局探索能力较弱,易陷入局部最优的不足,提出了两种改进策略:利用引力搜索算法更新蜉蝣的速度公式,以增强算法的全局探索能力和局部开发能力;对蜉蝣种群执行自适应反向学习策略,以提高算法的收敛速度及求解精度。将两种策略分别引入雌雄种群中得到六种算法变体。仿真结果表明,雄性种群混合引力搜索算法且雌性种群引入自适应反向学习策略的变体性能最好,命名为GSA-OMA算法。与8个元启发式优化算法相比,GSA-OMA算法具有更好的寻优精度和收敛速度。To address the shortcomings of the mayfly optimization algorithm(MA),which has a weak global exploration capability and easily falls into local optimum,two improvement strategies are proposed:updating the velocity equation of mayflies by using the gravitational search algorithm to enhance the global exploration capability and local exploitation capability of the MA algorithm;executing a adaptive opposition learning strategy on the mayfly population to improve the convergence speed and solution accuracy of the algorithm.Firstly,six variants of the algorithm are obtained by introducing the two strategies into the male and female populations respectively.Then,12 test functions are selected and numerical experiments are conducted,and the results show that the variant of the algorithm which mixes the male mayfly with the gravitational search algorithm and introduces adaptive opposition learning strategy into the female mayfly has the best performance,and is named the GSA-OMA algorithm.Finally,the GSA-OMA algorithm is compared experimentally with eight meta-heuristic optimization algorithms,and the results show that the GSA-OMA algorithm has better optimization finding accuracy and convergence speed.

关 键 词：蜉蝣优化算法 引力搜索算法 自适应反向学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]