一种融合粒子群算法的蝙蝠优化算法  

An optimized bat algorithm based on particle swarm optimization

作　　者：翁健高[1] 李道丰[1] 白琳[1] 易向阳[1] WENG Jian-gao;LI Dao-feng;BAI Lin;YI Xiang-yang(School of Computer and Electronic Information,Guangxi University,Nanning 530004,China)

机构地区：[1]广西大学计算机与电子信息学院,广西南宁530004

出　　处：《广西大学学报（自然科学版）》2018年第2期569-579,共11页Journal of Guangxi University（Natural Science Edition）

基　　金：国家自然科学基金资助项目(61662004);广西自然科学基金资助项目(2016GXNSFAA380215)

摘　　要：针对基本蝙蝠算法(BA)在寻优后期存在搜索性能差,寻优精度低,处理误差大,易陷入局部最优及早熟等缺陷,提出一种融合粒子群算法进行局部搜索的蝙蝠优化算法。该算法在局部搜索中,嵌入粒子群算法生成备选最优蝙蝠,并与基本蝙蝠算法生成的随机蝙蝠进行再竞争的方式优化种群,丰富了种群的多样性,提高了算法的全局搜索能力和局部搜索能力。Matlab环境下的仿真结果表明,改进后算法(PSOBA)在收敛速度及精度上均有明显提高,处理维度更高,是解决复杂函数优化问题的一种有效方法。To solve the inefficient search problems of the traditional bat algorithm in the later part of optimization process,such as poor optimization,serious deviation,easily falling into local optimal solution,an optimized bat algorithm based on particle swarm algorithm is proposed for optimizing local search process.The presented algorithm can produce some alternative best-bat operators in local search process,which competes against the other bat operators,produced by the traditional bat algorithm,and then enrich the diversity of the operator population and improve searching ability.The simulation under Matlab environment show that the improved algorithm(PSOBA)can improve the convergence speed and precision obviously,and has higher processing dimension,thus provides an effective method to solve the problem of complex function optimization.

关 键 词：蝙蝠算法 粒子群算法 竟争机制 函数优化 局部深度搜索 收敛速度 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]