传送带给料分批加工系统在线优化控制方法  

Online Optimal Control Method of Conveyor-serviced Batch Processing System

作　　者：吴松[1] 唐昊[1] 谭琦[1] Wu Song Tang Hao Tan Qi(School of Electrical Engineering and Automation, Hefei University of Technology, Hefei 230009, Chin)

机构地区：[1]合肥工业大学电气与自动化工程学院,安徽合肥230009

出　　处：《系统仿真学报》2017年第4期730-739,共10页Journal of System Simulation

基　　金：国家自然科学基金(61174186;61374158;71231004;61573126;60404009);高等学校博士学科点专项科研基金(20130111110007)

摘　　要：传送带给料分批加工系统中,工件动态到达,并配置有存放待加工工件的缓冲区,其加工主体为批处理设备。考虑工件属性差异,重点研究单机模型的在线优化控制问题。以前视距离为控制变量,无穷时段内的工件处理率最大为优化目标,建立了系统的优化模型。针对该模型中的工件分批决策,提出一种以批处理机加工周期内加工能力浪费比最小为准则的工件分批规则。对于该模型中的行动选择决策,文中引入Q学习优化算法,以求解最优前视控制策略。通过仿真实验,对算法的有效性进行了验证,并分析了不同分批策略及参数对系统性能的影响。In conveyor-serviced batch processing system, jobs arrive dynamically and are stored in a buffer to be further processed by the batch processing machine. Under the cases of non-identical job sizes, online optimal control of the system with a single machine was mainly concerned. Optimization model of the system was built by using look-ahead range as control variable. The objective is to maximize the job processing rate of the system in infinite horizon. Two decision processes are included in the model which are batching process and action-selection process. For the batching process, the rule of minimizing process-capacity wasting ratio of the machine during production period was proposed. And for the action-selection process, Q-learning algorithm was employed to derive the optimal look-ahead policy. The effectiveness of the proposed algorithms was demonstrated through the simulation experiments. Besides, the influence of some batching rules and physical parameters on system performance was showed.

关 键 词：批处理 差异工件 单机 在线优化 

分 类 号：TP202[自动化与计算机技术—检测技术与自动化装置]