基于元胞蝙蝠算法的复合式贴片机贴装调度优化  

Dual-gantry placement machine scheduling based on cellular bat algorithm

作　　者：陆曈曈 余竹玛 郑小东[2] 

机构地区：[1]常州大学商学院,常州213164 [2]三峡大学机械与动力学院,宜昌443002

出　　处：《现代制造工程》2017年第9期22-28,101,共8页Modern Manufacturing Engineering

基　　金：国家自然科学基金资助项目(51275274);湖北省自然科学基金项目(2014CFB665)

摘　　要：为了提高复合式贴片机的工作效率,研究了复合式贴片机的贴装过程优化问题,提出一种元胞蝙蝠算法。算法中提出一种分段的整数编码方法,并将元胞自动机理论融入蝙蝠算法中,以研究蝙蝠种群的交流结构和信息传递机制。采用多交叉算子自适应交叉的策略来提高算法的鲁棒性,设置精英文档来提高算法的收敛速度和维持种群的多样性,引入迭代互换操作来执行局部搜索以提高算法的收敛精度。通过对不同规模的实例进行计算,得到的结果表明,该算法能更快、更精确地收敛于全局最优值,能有效地实现复合式贴片机贴装过程优化,从而提高贴装效率。To improve the efficiency of dual-gantry placement machine, the placement process optimization problem is studied, a cellular bat algorithm is proposed. The algorithm proposes a piece-wise integer coding scheme. And the cellular automata is intro- duced into the bat algorithm to study the information communicating and exchanging mechanism. The strategy of self-adaptive multi crossover operators is adopted to improve the robustness of the algorithm. To accelerate the convergence and maintain the population diversity, an elitist external archive is established. An iterative swap procedure is borrowed to improve the convergence accuracy. The simulation resuhs show the proposed algorithm have a better performance in convergence rate and accuracy, which can achieve the optimization of the placement process to improve the assembly efficiency.

关 键 词：蝙蝠算法 复合式贴片机 贴装优化 元胞自动机 多交叉策略 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]