基于Agent的芯片制造生产线动态调度方法研究

摘要/Abstract

摘要： 基于智能体技术，提出了芯片制造生产线动态调度新方法，实现了投料调度、工件调度与设备维护调度的集成。首先，给出了基于智能体的动态调度模型，该模型中包括管理智能体、投料智能体、工件智能体、设备智能体、运输智能体与人员智能体。投料智能体用于实现投料控制，工件调度通过工件智能体与设备智能体之间的协商实现，设备维护调度由设备智能体实现。通过智能体间的合作，能够实现投料控制、工件调度与设备维护调度的协同进行。然后给出了工件智能体与设备智能体间协商使用的协商协议（即带有时间约束的单步协商协议），以及智能体决策中使用的调度算法（包括投料调度算法、工件调度算法与设备维护调度算法）。最后，通过实例，给出了方法的使用过程，并进行了模拟仿真。仿真结果表明，集成的调度方法能更好地优化模型的生产率、加工周期与设备利用率，最终提高准时交货率。

关键词: 芯片制造, 动态调度, 智能体, 集成, 协商协议, 调度算法

Abstract: :A new agent-based dynamic scheduling approach for semiconductor wafer fabrication was proposed, which integrated release control, dispatching and machine preventive maintenance scheduling. Firstly, an agent-based dynamic scheduling model was presented, which consisted of six kinds of agents, i.e. manager agent, input agent, workpiece agent, machine agent, transportation agent and operator agent. Release control was fulfilled by input agent, dispatching was performed by the negotiations between machine agents and workpiece agents and machine maintenance scheduling was implemented by the machine agents. The release control, dispatching and machine preventive maintenance scheduling were realized by agent collaboration. Secondly, the negotiation protocol among machine agents and workpiece agents, single-step negotiation protocol with time bound, was given. Thirdly, decision-making algorithms of agents were offered, including release control algorithm, dispatching algorithm and machine maintenance scheduling algorithm. Finally, the simulation results indicated that the proposed integration approach was advanced than original approaches without integration on throughput rate, cycle time, machine utility and on-time-delivery rate with better performance.

Key words: semiconductor wafer fabrication, dynamic scheduling, agent, integration, negotiation protocol, scheduling algorithm

中图分类号:

TP278

李莉，乔非，许潇红，吴启迪. 基于Agent的芯片制造生产线动态调度方法研究[J]. .

LI Li, QIAO Fei, XU Xiao-hong, WU Qi-di. Research on agent-based dynamic scheduling approach for semiconductor wafer fabrication[J]. .

参考文献

［1］ SUBHASH C S, SAMEER T S. Reduction of average cycle time at a wafer fabrication facility［R］. Blacksburg，VA，USA： Virginia Tech., 2001.

[2] SPEARMAN M L, WOODRUFF D L, HOPP W J. CONWIP： a pull alternative to kanban［J］. International Journal of Production Research, 1990, 28(10)： 879-894.

[3] WEIN L M. Scheduling semiconductor wafer fabrication［J］. IEEE Transactions on Semiconductor Manufacturing, 1988, 1（2）： 115-129.

[4] DABBAS R M, CHEN H N, JOHN W F, et al. A combined dispatching criteria approach to scheduling semiconductor manufacturing systems［J］. Computers& Industrial Engineering, 2001, 39(3)： 307-324.

[5] SCOTT J M, KASIN O. Scheduling complex job shops using disjunctive graphs： a cycle elimination procedure［J］. International Journal of Production Research, 2003, 41(5)： 981-994.

[6] SRINIVASAN M M, LEE H S. Production-inventory systems with preventive maintenance［J］.IIE Transactions, 1996,28(8)：879-890.

[7] CHEUNG K L, HAUSMANN V H. Joint optimization of preventive maintenance and safety stocks in a unreliable production environment［J］. Naval Research Logistics, 1997, 44(3)： 257-272.

[8] DAS T, SARKUR S. Optimal preventive maintenance in a production inventory system［J］. IIE Transactions on Quality and Reliability Engineering, 1999, 31(6)： 537-549.

[9] YAO X, FU M, MARCUS S I, et al. Incorporating production planning into preventive maintenance scheduling in semiconductor fabs［A］. Proceedings of the International Conference on Modeling and Analysis of Semicondutor Manufacturing(MASM,2002)［C］. Tempe,AZ,USA:Arizona Publisher, 2002.84-89.

[10] ALBERT D B. A survey of factory control algorithms which can be implemented in a multi-agent herarchy： dispatching, scheduling and pull［J］. Journal of Manufacturing System, 1998, 6(3)： 276-289.

[1]	冯春,张祎伟,黄成,姜文彪,武之炜. 双足机器人步态控制的深度强化学习方法[J]. 计算机集成制造系统, 2021, 27(8): 2341-2349.
[2]	李文俊,杨学强,杜家兴. 基于云计算的装备保障信息系统集成[J]. 计算机集成制造系统, 2021, 27(7): 1941-1950.
[3]	马玉敏,陆晓玉,乔非,沈一路. 基于极限学习机的复杂制造系统动态调度[J]. 计算机集成制造系统, 2021, 27(4): 1081-1088.
[4]	裴植,万明重,杜蕊,李英德,陈勇. 多充电桩下考虑运载机械释放时间的充电调度[J]. 计算机集成制造系统, 2021, 27(4): 1089-1098.
[5]	杨小佳,刘建军,陈庆新,毛宁. 变扰动强度下柔性装配作业车间调度性能分析[J]. 计算机集成制造系统, 2021, 27(3): 800-814.
[6]	伍京华,王佳莹,张富娟,韩佳丽,叶慧慧. 基于Agent的信任的情感劝说决策模型[J]. 计算机集成制造系统, 2021, 27(3): 887-898.
[7]	曹远冲,熊辉,庄存波,刘检华,宁伟航. 基于数字孪生的复杂产品离散装配车间动态调度[J]. 计算机集成制造系统, 2021, 27(2): 557-568.
[8]	魏莹,刘冠,李锋. 基于社交网络效应的产品设计研究[J]. 计算机集成制造系统, 2021, 27(12): 3591-3603.
[9]	莫超雄,刘建军,陈庆新,毛宁,胡常伟. 集成化定制需求下多地总装作业过程敏捷协同管控系统[J]. 计算机集成制造系统, 2021, 27(11): 3103-3119.
[10]	葛艳,王爱民,叶介然. 基于遗传退火算法的质检扰动应对方法[J]. 计算机集成制造系统, 2021, 27(11): 3159-3171.
[11]	张文杰,王国新,阎艳,褚厚斌,王晶,曹志松. 基于数字孪生和多智能体的航天器智能试验[J]. 计算机集成制造系统, 2021, 27(1): 17-34.
[12]	伍京华,陈虹羽,汪文生. 基于Agent的情感劝说的舆情交互及产生模型[J]. 计算机集成制造系统, 2021, 27(1): 249-259.
[13]	吴倩云,谢乃明,邵雨婷. 考虑时间窗和装载约束的装配线集成物流调度[J]. 计算机集成制造系统, 2020, 26(第3): 806-814.
[14]	彭琨琨,李新宇,高亮,邓旭东. 可调加工时间炼钢-连铸的灰狼优化调度算法[J]. 计算机集成制造系统, 2020, 26(第1): 58-65.
[15]	陶俐言,赵鹏翡,陈冉冉. 基于动态机器故障率的并联加工系统资源多目标调度[J]. 计算机集成制造系统, 2020, 26(第1): 66-73.