一种改进的自适应变异蝙蝠算法  

An Improved Algorithm for Adaptive Mutation Bat

作　　者：盛孟龙[1] 贺兴时[1] 王慧敏[1] 

机构地区：[1]西安工程大学理学院,陕西西安710048

出　　处：《计算机技术与发展》2014年第10期131-134,共4页Computer Technology and Development

基　　金：陕西省软科学基金项目(2012KRM58);陕西省教育自然科学基金项目(12JK0744)

摘　　要：针对蝙蝠算法在解决高维复杂问题时容易陷入局部最优解和精确度不高的问题,文中提出了一种改进的蝙蝠算法。在原算法的基础上,引入一种交叉变换的方式更新蝙蝠群体的位置,一方面是为了提高蝙蝠算法的遍历性,另外还可以减小蝙蝠算法陷入局部最优解的可能性。模拟蝙蝠发声的音量变化,采用自适应的变换的方式改进蝙蝠算法最优解的选择模式,达到提高算法的精度和收敛速度的目的。最后通过标准的测试函数对改进后的算法进行数值模拟,结果显示,改进后的算法较为有效。In view of the problem which is easy to fall into local optimal solution and the accuracy is not high in solving high-dimensional complex problems for bat algorithm,propose an improved algorithm of bat in this paper. On the basis of the original algorithm,introduce a cross transform to update the location of the bat population,one hand is to enhance the traverses of bat algorithm,on the other hand can reduce the possibility of falling into local optimal solution. Analog bat sound volume changes,using an way of adaptive transform to im-prove the selection mode of bat algorithm optimal solution,achieving the purpose of improving the accuracy and convergence rate. Final-ly,the standard test function is used to conduct the numerical simulation for the improved algorithm,the results show that the improved al-gorithm is more effective.

关 键 词：蝙蝠算法 交叉变换 Beat分布 自适应变异 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]