樽海鞘群算法基于动力学模型的改进  

Improvements of slap swarm algorithm based on dynamic model

作　　者：雷灏 赵品彰 汪东华 陈柏屹[2] LEI Hao;ZHAO Pinzhang;WANG Donghua;CHEN Boyi(Jiangsu Institute of Metrology,Nanjing 210049,China;College of Astronautic,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China)

机构地区：[1]江苏省计量科学研究院,江苏南京210049 [2]南京航空航天大学航天学院,江苏南京210016

出　　处：《系统工程与电子技术》2024年第1期300-308,共9页Systems Engineering and Electronics

基　　金：江苏省基础研究计划(自然科学基金)青年基金项目(BK20200437);江苏省卓越博士后计划;国家自然科学基金青年基金(62103187);中央高校基本科研业务费(NT2022025);江苏省市场监管局科技计划项目(KJ196012)资助课题。

摘　　要：针对樽海鞘群算法(salp swarm algorithm,SSA)中参数含义不明确、收敛性不确定的问题,构建了SSA的差分动力学模型,定义了领导者选择机制、领导者游走机制、跟随者偏序学习机制,重点针对跟随者偏序学习机制分析了系统的收敛性,面向领导者游走机制与跟随者偏序学习机制提出了算法全局最优收敛的充分条件。基于动力学分析结果提出了樽海鞘群异质定常跟随率与偏序多驱动机制的改进方法,仅对算法结构与参数进行了调整,在未增加计算量的情况下提高了算法的性能,通过仿真分析验证了改进的有效性。Focusing on the problems of unclear parameter meaning and uncertain convergence in salp swarm algorithm(SSA),the differential dynamics model of SSA is constructed,including leader selection mechanism,leader walking mechanism,and follower partial order learning mechanism.The convergence of the system is analyzed with emphasis on the follower partial order learning mechanism.The sufficient conditions for the global optimal convergence of the algorithm are proposed for the leader-walking mechanism and the follower partial order learning mechanism.Based on the analytical result of dynamic behavior,an improved method of heterogeneous steady following rate and partial order multi-drive mechanism of salp swarm is proposed.Only the structure and parameters of the algorithm are adjusted,and the performance of the algorithm is improved without increasing the amount of calculation.The effectiveness of the proposed algorithm is verified by simulation analysis.

关 键 词：樽海鞘群算法 智能算法 群体动力学 收敛性分析 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]