改进GA机制融合的二进制蜂群算法研究  

Research Based on Improved Binary Artificial Bee Colony Algorithm with GA Mechanism

作　　者：霍凤财[1] 任伟建[1] 杜颖[1] 刘洋[1] HUO Feng-cai REN Wei-jian DU Ying LIU Yang(School of Electrical Information Engineering, Northeast Petroleum University, Daqing 163318, China)

机构地区：[1]东北石油大学电气信息工程学院,黑龙江大庆163318

出　　处：《数学的实践与认识》2017年第2期166-175,共10页Mathematics in Practice and Theory

基　　金：国家自然科学基金(61374127;61422301;51404073);中国博士后科学基金(2014M550180);中国石油科技创新基金(2013D-5006-0209);黑龙江省博士后科研启动基金(LBH-Q12143);东北石油大学青年基金(2013NQ105);黑龙江省教育厅科学技术研究项目(12511014;12541090)

摘　　要：为了克服人工蜂群算法蜜源更新过程中的随机性并保留蜜源中个体序列合理的组合形式,通过分析基本蜂群算法更新公式的机理,提出一种改进GA(Genetic A1gorithm)机制融合的二进制蜂群算法.算法以二进制编码,首先依概率对任意两蜜源进行"去同存异"操作后随机排列,将排列结果放入到其中某个体中形成新个体.然后依概率进行二进制个体的"翻转"操作,上述两种操作从其本质上相当于GA的类交叉和类变异操作;其次利用GA机制收敛性的证明方式在理论上证明算法是收敛的.最后通过应用不同特性的多维基准函数和算法之间的比较验证改进蜂群算法具有良好的收敛能力和鲁棒性.In order to overcome the randomness in the process of updating nectar and retain reasonable combinations of individual sequences in the artificial bee colony algorithm,an improved binary bee colony algorithm based on Genetic Alogrithm（GA） mechanism is proposed by analysizing the mechanism of algorithm＇s updating formula.Binary encoding is adopted,firstly,a new individual is arranged by random one that any two individuals exchange in use of ＂remove the same reserve the difference＂.Then binary individual is flipped by probability,all these operations look like crossing and mutation in GA from the nature.Secondly,this algorithm is proved to be convengent in the theory of GA mechanism.Finally,application in different characters＇ multi-dimensional benchmark functions and comparison with different algorithms verify that the proposed bee colony algorithm has better convergence ability and robustness.

关 键 词：GA机制 二进制 去同存异 蜂群算法 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]