动态车间作业调度问题中调度规则算法研究综述  

Survey of dispatching rules for dynamic Job-Shop scheduling problem

作　　者：范华丽 熊禾根[1] 蒋国璋[1] 李公法[1] 

机构地区：[1]武汉科技大学机械自动化学院,武汉430081

出　　处：《计算机应用研究》2016年第3期648-653,共6页Application Research of Computers

基　　金：国家自然科学基金资助项目(71271160);湖北省教育厅科研计划重点项目(D20121102)

摘　　要：调度规则是解决实际生产中的动态车间作业调度问题的有效方法,但它一般只在特定调度环境下性能较好,当环境发生变化时,就需要进行实时选择和评价。对调度规则的实时选择和评价方法进行综述,以研究实际生产中动态车间的实时调度问题。对调度规则的发展、分类以及特点进行了概述,并对调度规则的选择和评价方法进行了总结;详细介绍了调度规则的选择方法,包括使用较多的稳态仿真方法和表现较好的人工智能方法,并给出了仿真方法、专家系统、机器学习方法以及人工神经网络方法,用于调度规则的选择时所取得的研究成果和结论,以及调度规则的评价指标和评价方法。最后针对调度规则存在的不足,指出了未来的研究方向。Dispatching rule is an effective method for solving dynamic Job-Shop scheduling problem in practical production.However,its biggest problem lies in that usually it only has good performance in the specific scheduling environment,so realtime selection and evaluation are needed. To study the real-time scheduling problem with dynamic shop in practical production,this paper surveyed the methods for the selection and evaluation of dispatching rules. It reviewed the development,classification and characteristics of dispatching rules,and summarized the research hotspots of dispatching rules including the selection and evaluation methods. It introduced the selection methods of dispatching rules in detail which included the popular steady state simulation method and the effective artificial intelligence method. In addition,it presented the research results and conclusions of simulation methods,expert system,machine learning methods and artificial neural network methods that were applied to the selection of dispatching rules. Besides,it introduced the measures and methods for the evaluation of dispatching rules. Finally this paper pointed out the direction of future research aiming at the shortcomings of the existing dispatching rules.

关 键 词：动态车间作业调度问题 调度规则 人工智能 机器学习 人工神经网络 

分 类 号：TP182[自动化与计算机技术—控制理论与控制工程] TP301.6[自动化与计算机技术—控制科学与工程]