计算机工程与应用 ›› 2021, Vol. 57 ›› Issue (21): 59-67.DOI: 10.3778/j.issn.1002-8331.2103-0390

• 热点与综述 • 上一篇    下一篇

制造车间自动导引车调度新进展

曹立佳,刘洋   

  1. 1.四川轻化工大学 计算机科学与工程学院,四川 宜宾 644000
    2.人工智能四川省重点实验室,四川 自贡 643000
    3.四川轻化工大学 自动化与信息工程学院,四川 宜宾 644000
  • 出版日期:2021-11-01 发布日期:2021-11-04

Recent Advances in Scheduling Optimization of Automated Guided Vehicles in Manufacturing Workshops

CAO Lijia, LIU Yang   

  1. 1.School of Computer Science and Engineering, Sichuan University of Science & Engineering, Yibin, Sichuan 644000, China
    2.Artificial Intelligence Key Laboratory of Sichuan Province, Zigong, Sichuan 643000, China
    3.School of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin, Sichuan 644000, China
  • Online:2021-11-01 Published:2021-11-04

摘要:

随着制造企业生产自动化程度加深,自动导引车(AGV)成为运输和搬运环节的主角。近年来,制造车间AGV调度主要是建立双目标或多目标函数的优化模型,采用智能优化方法进行求解,其中遗传算法以广度搜索能力强的优势成为当今最常用的算法框架。另外,当今主流的还有混合算法,它使各种算法和算子的优势集中在一起,以得到更好的优化表现。就最新的制造车间AGV调度优化所研究的问题模型进行了归纳和总结,给出了主流的优化结果表现形式,并将求解优化模型主要采用的研究方法分为基于遗传算法框架的算法、其他智能优化方法和其他优化方法三大类进行讨论,在每一大类中提取重要的关键字以及交叉学科词汇进行汇总。在此基础之上总结出当今AGV调度研究中的两点不足之处,并结合当今的热点(大数据、人工智能等)对未来的研究方向提出了几条建议。

关键词: 制造车间, 自动导引车, 调度, 智能优化, 遗传算法, 混合算法

Abstract:

With the development of production automation in manufacturing enterprises, Automatic Guided Vehicle(AGV) has become the significant role in transportation and handling. In recent years, the key step of scheduling optimization of AGV in manufacturing workshops is to establish the optimization model of double-objective or multi-objective function, which is solved by intelligent optimization methods, in which genetic algorithm has become the most popular algorithm framework because of its exploration ability. In addition, hybrid methods are also widely used, because of these methods make the advantages of various algorithms and operators together and aim to achieve better optimization performance. The models of the latest AGV scheduling optimization in manufacturing workshops and the mainstream optimization results are summarized in this paper. The research methods presented to solve the optimization model are divided into three categories:algorithms based on the framework of genetic algorithm, other intelligent optimization methods and other optimization methods. In each category, important keywords and interdisciplinary vocabularies are extracted and summarized. Furthermore, the two disadvantages in the current research on AGV scheduling and many suggestions for the future research direction combined with the current hot spots(big data, artificial intelligence, et al.) are also given at the end of this article.

Key words: manufacturing workshops, automated guided vehicle, scheduling, intelligent optimization, genetic algorithm, hybrid method