天牛须搜索与遗传的混合算法  

Hybrid Optimization Algorithm Based on Beetle Antennae Search and Genetic Evolution

作　　者：赵玉强 钱谦[1,2] 周田江 伏云发 ZHAO Yu-qiang;QIAN Qian;ZHOU Tian-jiang;FU Yun-fa(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China;Yunnan Key Laboratory of Computer Technology Applications,Kunming 650500,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,昆明650500 [2]云南省计算机技术应用重点实验室,昆明650500

出　　处：《小型微型计算机系统》2020年第7期1438-1445,共8页Journal of Chinese Computer Systems

基　　金：国家自然科学基金面上项目(81470084)资助;国家自然科学基金地区科学基金项目(61463024)资助。

摘　　要：天牛须搜索算法(BAS)具有搜索快和执行简单的特点,但在多峰复杂函数优化中易陷入局部极值.遗传算法(GA)的全局搜索能力强,但收敛速度缓慢,收敛精度不高.针对二者的优缺点,本文提出天牛须搜索与遗传进化混合的优化算法.首先,在BAS算法中设计多方向探索反馈策略来增加算法的搜索能力,并将其嵌入到GA算法中,加快GA的全局收敛速度,然后在GA算法中采用扩展的多子代竞争交叉和自适应调整参数的方式来维持种群的多样性,避免了局部极值问题,进一步提高了算法的寻优性能.对测试函数的优化结果分析表明,与其它几种混合算法相比,该混合算法具有更高的收敛精度和优化性能,并且在复杂函数中有更好的普适性.The beetle antenna search algorithm(BAS)has the characteristics of fast search and simple execution,but it is easy to fall into the local extremum in the optimization of multi-peak complex function.The global search ability of genetic algorithm(GA)is strong,but the convergence speed is slow and the convergence accuracy is not high.Based on the advantages and disadvantages of the above two algorithms,this paper proposes an new optimization algorithm by mixing BAS and GA.Firstly,the multi-directional exploration feedback strategy is designed to increase the search ability of the BAS algorithm,and then the BAS algorithm is embedded in GA to obtain better solution in a short time,thus speeding up the global convergence speed of GA.In addition,the extended crossover operator and adaptive parameter adjustment method are used in GA to maintain the diversity of the population,which is helpful to avoid the local extreme problem and further improve the optimization performance.According to the optimization results of the test functions,the proposed hybrid algorithm has higher convergence accuracy and optimization performance than other hybrid algorithms.

关 键 词：天牛须搜索算法 遗传算法 函数优化 算法融合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]