基于神经元动态规划的可重入生产系统调度的仿真框架  

Simulation Framework of Scheduling Re-entrant Lines Based on Neuro-Dynamic Programming

作　　者：王颖[1] 朱顺痣[1] 许威[1] 缪克华[1] 李茂青[1] 

机构地区：[1]厦门大学系统与控制研究中心,福建厦门361005

出　　处：《信息与控制》2007年第2期218-223,共6页Information and Control

摘　　要：提出一个基于神经元动态规划解决可重入生产系统调度问题的仿真框架.根据可重入生产系统的特点建立状态集,并将调度问题表示成相应的马尔可夫决策过程.选择合理的性能指标,采用神经元动态规划产生每一步的调度,并在仿真中优化策略.仿真算例验证了该方法的有效性,三种调度策略的结果比较表明了神经元动态规划方法的优越性.本仿真框架还可拓展至其他类型的生产调度问题.A simulation framework of scheduling re-entrant lines with Neuro-Dynamic Programming （NDP） is presented. The state set is constructed based on the characteristics of re-entrant lines, and the scheduling problem is described as the corresponding Markov decision process. Proper performance index is selected, and each scheduling decision is produced and improved in simulation with NDP. An example is given to illustrate the validity of the method. The comparison of three scheduling policies indicates the superiority of NDP in scheduling re-ehtrant lines. The presented simulation framework can be extended to scheduling of other kinds of production systems.

关 键 词：仿真框架 可重入生产系统 神经元动态规划 调度 

分 类 号：TP278[自动化与计算机技术—检测技术与自动化装置]