多策略混合改进的海洋捕食者算法及其工程应用  

Enhancing marine predator algorithm with hybrid multi-strategy and its application

作　　者：朱学敏 刘升[1] 朱学林 游晓明[1] Zhu Xuemin;Liu Sheng Zhu;Xuelin;You Xiaoming(School of Management,Shanghai University of Engineering Sciences,Shanghai 201620,China)

机构地区：[1]上海工程技术大学管理学院,上海201620

出　　处：《国外电子测量技术》2023年第5期125-134,共10页Foreign Electronic Measurement Technology

摘　　要：为解决海洋捕食者算法(MPA)自适应能力有限、易陷入局部最优等问题,提出融合多策略改进的海洋捕食者算法(EMPA)。首先,在种群初始化阶段,采用精英反向学习策略初始化猎物种群,丰富种群的多样性。其次,在阶段更新过程中,设计出具有更强非线性收敛性的自适应惯性权重,控制捕食者在整个过程中的位置更新。在此基础之上,在等速比阶段,引入算术优化算子指导猎物搜索空间,平衡种群的全局勘探和局部开采。进一步,在海洋记忆存储阶段,采用t分布变异策略对猎物位置进行变异,增强个体在迭代后期跳出局部最优的能力。通过在8个测试函数上的算法性能测试及与著名算法的比较,验证了EMPA算法的优越性。最后,针对传统方法设计的断路器储能弹簧结构参数设置不合理、分断性能差等缺陷,应用EMPA对断路器储能弹簧进行优化设计,实验结果表明,EMPA算法的设计结果更加小型化、分断性能更优。To address the problems of limited self-adaptive capability and easy to fall into local optimality of the marine predator algorithm(MPA),an enhancing marine predator algorithm with hybrid multi-strategy(EMPA)is proposed.Firstly,in the population initialization stage,the elite opposition-based learning strategy is used to initialize the prey population and enrich the diversity of the population.Secondly,in the phase update stage,the adaptive inertia weight with stronger nonlinear convergence is designed to replace the parameter CF,to control the position update of predators throughout the process,so as to improve the search efficiency of the algorithm.On this basis,in the isochronous ratio phase,arithmetic optimization operators are introduced to guide the prey search space,to balance the global search and local exploitation of individuals in the population.Further,in the marine memory storage stage,the t-distribution variation strategy is used to variate the prey position to enhance the ability of individuals to jump out of the local optimum in the late iteration.Through the performance test of the algorithm on eight benchmark functions and the comparison with famous algorithms,the superiority of the EMPA algorithm is verified.Finally,for the defects of unreasonable setting of structural parameters and poor breaking performance of circuit breaker energy storage spring designed by traditional methods,EMPA is applied to optimize the design of circuit breaker energy storage spring,and the experimental results show that the design results of EMPA algorithm are more miniaturized and have better breaking performance.

关 键 词：海洋捕食者算法 精英反向学习 算术优化算子 t-分布变异 储能弹簧设计 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]