具有禁忌策略的蜂群算法评定圆柱度误差  

Cylindricity error evaluation using artificial bee colony algorithm with tabu strategy

作　　者：罗钧[1] 卢嘉江[1] 陈伟民[1] 付丽[1] 刘学明 张平 陈建端 

机构地区：[1]重庆大学光电技术及系统教育部重点实验室,重庆400030 [2]兵器工业296区域计量站,重庆400050

出　　处：《重庆大学学报（自然科学版）》2009年第12期1482-1485,共4页Journal of Chongqing University

基　　金：国防科工委国防军工计量'十一五'计划重点资助项目(B20301118)

摘　　要：针对最小二乘法评定误差较大,遗传、蚁群等仿生算法设置参数较多、收敛速度较慢的问题,结合圆柱度误差评定的特点,提出采用蜂群算法,来实现圆柱度误差的最小区域法评定。该算法借鉴了禁忌搜索算法的禁忌策略,用禁忌表存储局部最优解,增强对参数Limit的控制作用,提高全局搜索能力。实验研究结果表明,该方法能收敛到全局最优解,并且计算结果稳定,收敛速度很快,平均运算时间在1.2s左右,适用于三坐标测量机等实时处理系统。For cylindricity error evaluation,the Least Squares Method （LSM） is not good enough because of the big error,while the bionics algorithms such as Genetic and Ant Colony Algorithm need to set many parameters and converge slowly,an Artificial Bee Colony Optimization Algorithm is proposed to evaluate the minimum zone cylinder （MIC）. This Algorithm refers the tabu strategy for tabu search algorithm to use the Tabu table to save the local optimization results. It enhances the control effect of parameter limit and improves the global convergence ability. Experiment results indicate that this method can converge to the global optimization very quickly. The average runtime is nearly 1.2 s. It is applicable to the real-time processing system such as Three-Coordinate Measuring Machine.

关 键 词：蜂群算法 禁忌策略 最小区域法 圆柱度 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置] TH115[自动化与计算机技术—控制科学与工程]