基于反向学习机制的蝙蝠算法  

Bat Algorithm Based on Opposition Learning Mechanism

作　　者：岳伟娜 马吉明[1] 苏日建[1] 郭盛楠[1] 

机构地区：[1]郑州轻工业学院计算机与通信工程学院,河南郑州450002

出　　处：《湖北民族学院学报（自然科学版）》2016年第3期251-255,共5页Journal of Hubei Minzu University(Natural Science Edition)

基　　金：国家自然科学基金项目(61374014);河南省科技攻关项目(132102210056;142102210080)

摘　　要：针对蝙蝠算法存在收敛速度慢,寻优精度低问题,提出一种基于反向学习的蝙蝠算法,该算法具有易跳出局部最优,寻优精度高,种群多样性且鲁棒性好等特点.通过对6个典型的测试函数进行仿真实验,结果表明该算法是行之有效的,且在求解多峰函数时运算的效果更好.Aiming at the problem that the firefly algorithm has slow convergence and low precision,an improved Bat algorithm based on opposition learning mechanism is proposed.The proposed algorithm is characterized by high precision and good robustness,and it can effectively jump out the local optimum.6 typical test functions are simulated and the results show that the algorithm is effective and feasible. What＇ s more,the algorithm also has excellent arithmetic performance in solving an optimization problem with multi-modal function.

关 键 词：蝙蝠算法 反向学习 多样性 鲁棒性 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]