基于仿真的可重入生产系统的神经元动态规划调度研究
|
摘要
可重入生产系统是以半导体和薄胶片生产为代表的一类复杂生产系统,在微电子行业飞速发展的今天,可重入生产系统已受到工业界和学术界的广泛关注。
本文对可重入生产系统的描述、模型、性能及调度等方面进行了系统的研究,提出一些新的思想和方法,主要的工作和创新之处总结如下:
1、建立可重入生产系统状态空间及调度集,计算可重入生产系统的状态转移概率表明该系统是连续的Markov决策过程,并提出系统的待调度状态集及非待调度状态集的生成算法。
2、针对可重入生产系统提出瓶颈工作站和阻塞状态的数学描述,证明单瓶颈工作站是系统中最忙碌、机器利用率最高的工作站,进而提出模型的简化方法:针对单瓶颈系统可直接简化非瓶颈工作站;针对多瓶颈系统,则提出NBJP调度策略作为简化非瓶颈工作站时的还原补偿策略;并提出有条件的相邻工序合并方法。最后给出系统简化及调度策略的还原算法。
3、针对二站封闭式可重入生产系统证明了平均输出率和双机生产时间作为性能指标的等价性,并将结论推广至多站系统,在此基础上推导出封闭式可重入生产系统连续Markov决策过程的动态规划模型。对封闭式和开放式可重入生产系统的连续Markov决策过程分别采用不同的离散化方法,并人工构造终止状态,获得两种投料策略下系统离散Markov决策过程的随机最短路径动态规划模型。
4、针对可重入生产系统的动态规划模型,基于神经元动态规划设计了可重入生产系统的调度仿真框架,分别在封闭式和开放式投料策略下,选择合适的初始状态、函数结构、特征向量和归一化方法,并提出将启发式策略的性能指标作为特征分量的想法,针对该动态规划模型设计了采用神经元动态规划方法进行迭代求解的算法,并比较分析了封闭式和开放式可重入生产系统的平均产品输出率及平均机器利用率。
5、针对HP公司提出的可重入生产系统Benchmark标准问题—TRC模型重新建立了考虑机器故障和维修时间的可重入生产系统的状态表示、状态分类、调度集、一步转移概率和一步转移代价体系,采用模型简化方法对三种参数设置下的TRC模型进行简化,选择合适的投料策略,设定合理的特征向量及归一化方法,采用神经元动态规划求解其调度策略,并与以往的调度结果进行比较,得到满意的结果。TRC模型调度研究的成功全面证明了本文建立的可重入生产系统的调度体系的有效性和优越性。
Re-entrant lines are a class of complex production systems abstracted from semiconductor and film manufacturing systems. With the development of microelectronics industry, Re-entrant lines have drawn much attention of academia and industry.
System descriptions, modeling, performance analysis and scheduling of Re-entrant lines are explored and some new ideas and methods are presented in this paper, whose major contributions are as follows:
1. The Re-entrant line is described mathematically, where states space and scheduling sets are built; transition probability has been derived to prove scheduling a Re-entrant line is a Continuous-Time Markov Decision Process (CTMDP). Then the algorithm of building vanishing states and tangible states is designed.
2. The mathematics descriptions of bottleneck workstation and block state are presented for Re-entrant lines. It has been proven that single-bottleneck station is the busiest workstation and with the highest machine utility, upon which the model simplification method is proposed. For single-bottleneck system, the non-bottleneck stations would be omitted directly; for multi-bottleneck system, the NBJP scheduling policy is developed as compensation for omission non-bottleneck stations. Then consecutive job stages can be united to one job stage under some condition. The simplification and reversion algorithms are derived for applications.
3. The equivalence of mean throughput and double-machine working time as performance index is proven for two-station closed Re-entrant lines, which has been extended to multi-station closed re-entrant lines. Based on this conclusion, the dynamic programming model for CTMDP of Re-entrant lines is developed. Different methods are adopted to discretize the CTMDPs of closed and open Re-entrant lines. Terminal state is constructed to obtain the stochastic shortest path model of Discrete-Time Markov Decision Process (DTMDP) with the two release policies.
4. Simulation framework of scheduling a re-entrant line based on Neuro-Dynamic Programming (NDP) is constructed for the dynamic programming model, and the corresponding iteration algorithm is designed. With the closed and open release policies, initial states, function structures, features and its uniformization method are selected and explored properly. The idea that the performance indexes of heuristic policies are applied as features is presented and realized, simulation results are satisfactory. The throughput and machines utilization are compared and analyzed for open and closed release policies.
5. Machine breakdowns and repair time taken into account, the states space, scheduling set, transition probability and transition cost are rebuilt for HP’s benchmark question, TRC model. Model simplification method is applied respectively to the TRC models with three different configurations. Proper release policy is selected, features and their uniformization are properly set, NDP is applied to obtain the scheduling policy. Simulation results of scheduling policy by NDP are satisfactory, which verifies the validity and superiority of the whole scheduling policy optimization system built by this dissertation.
本文对可重入生产系统的描述、模型、性能及调度等方面进行了系统的研究,提出一些新的思想和方法,主要的工作和创新之处总结如下:
1、建立可重入生产系统状态空间及调度集,计算可重入生产系统的状态转移概率表明该系统是连续的Markov决策过程,并提出系统的待调度状态集及非待调度状态集的生成算法。
2、针对可重入生产系统提出瓶颈工作站和阻塞状态的数学描述,证明单瓶颈工作站是系统中最忙碌、机器利用率最高的工作站,进而提出模型的简化方法:针对单瓶颈系统可直接简化非瓶颈工作站;针对多瓶颈系统,则提出NBJP调度策略作为简化非瓶颈工作站时的还原补偿策略;并提出有条件的相邻工序合并方法。最后给出系统简化及调度策略的还原算法。
3、针对二站封闭式可重入生产系统证明了平均输出率和双机生产时间作为性能指标的等价性,并将结论推广至多站系统,在此基础上推导出封闭式可重入生产系统连续Markov决策过程的动态规划模型。对封闭式和开放式可重入生产系统的连续Markov决策过程分别采用不同的离散化方法,并人工构造终止状态,获得两种投料策略下系统离散Markov决策过程的随机最短路径动态规划模型。
4、针对可重入生产系统的动态规划模型,基于神经元动态规划设计了可重入生产系统的调度仿真框架,分别在封闭式和开放式投料策略下,选择合适的初始状态、函数结构、特征向量和归一化方法,并提出将启发式策略的性能指标作为特征分量的想法,针对该动态规划模型设计了采用神经元动态规划方法进行迭代求解的算法,并比较分析了封闭式和开放式可重入生产系统的平均产品输出率及平均机器利用率。
5、针对HP公司提出的可重入生产系统Benchmark标准问题—TRC模型重新建立了考虑机器故障和维修时间的可重入生产系统的状态表示、状态分类、调度集、一步转移概率和一步转移代价体系,采用模型简化方法对三种参数设置下的TRC模型进行简化,选择合适的投料策略,设定合理的特征向量及归一化方法,采用神经元动态规划求解其调度策略,并与以往的调度结果进行比较,得到满意的结果。TRC模型调度研究的成功全面证明了本文建立的可重入生产系统的调度体系的有效性和优越性。
Re-entrant lines are a class of complex production systems abstracted from semiconductor and film manufacturing systems. With the development of microelectronics industry, Re-entrant lines have drawn much attention of academia and industry.
System descriptions, modeling, performance analysis and scheduling of Re-entrant lines are explored and some new ideas and methods are presented in this paper, whose major contributions are as follows:
1. The Re-entrant line is described mathematically, where states space and scheduling sets are built; transition probability has been derived to prove scheduling a Re-entrant line is a Continuous-Time Markov Decision Process (CTMDP). Then the algorithm of building vanishing states and tangible states is designed.
2. The mathematics descriptions of bottleneck workstation and block state are presented for Re-entrant lines. It has been proven that single-bottleneck station is the busiest workstation and with the highest machine utility, upon which the model simplification method is proposed. For single-bottleneck system, the non-bottleneck stations would be omitted directly; for multi-bottleneck system, the NBJP scheduling policy is developed as compensation for omission non-bottleneck stations. Then consecutive job stages can be united to one job stage under some condition. The simplification and reversion algorithms are derived for applications.
3. The equivalence of mean throughput and double-machine working time as performance index is proven for two-station closed Re-entrant lines, which has been extended to multi-station closed re-entrant lines. Based on this conclusion, the dynamic programming model for CTMDP of Re-entrant lines is developed. Different methods are adopted to discretize the CTMDPs of closed and open Re-entrant lines. Terminal state is constructed to obtain the stochastic shortest path model of Discrete-Time Markov Decision Process (DTMDP) with the two release policies.
4. Simulation framework of scheduling a re-entrant line based on Neuro-Dynamic Programming (NDP) is constructed for the dynamic programming model, and the corresponding iteration algorithm is designed. With the closed and open release policies, initial states, function structures, features and its uniformization method are selected and explored properly. The idea that the performance indexes of heuristic policies are applied as features is presented and realized, simulation results are satisfactory. The throughput and machines utilization are compared and analyzed for open and closed release policies.
5. Machine breakdowns and repair time taken into account, the states space, scheduling set, transition probability and transition cost are rebuilt for HP’s benchmark question, TRC model. Model simplification method is applied respectively to the TRC models with three different configurations. Proper release policy is selected, features and their uniformization are properly set, NDP is applied to obtain the scheduling policy. Simulation results of scheduling policy by NDP are satisfactory, which verifies the validity and superiority of the whole scheduling policy optimization system built by this dissertation.
引文
[1] 国家中长期科学和技术发展规划纲要(2006━2020 年)[Z]. 2006.
[2] Leachman, R.C. and D.A. Hodges. Benchmarking Semiconductor Manufacturing[J]. IEEE Transactions on Semiconductor Manufacturing, 1996, 9(2): 158-169.
[3] Pickett, B. and M. Zuniga. Modeling, scheduling, and dispatching in the dynamic environment of semiconductor manufacturing at FASL, Japan[C]. in SEMI Advanced semiconductor manufacturing conference. 1997. 448-450.
[4] Potoradi, J., S.J. Mason, and J.W. Fowler. Using Simulation-based Scheduling to Maximize Demand Fulfillment in a Semiconductor Assembly Facility[C]. in Proceedings of the 2002 Winter Simulation Conference. 2002. 1857-1861.
[5] Malmstrom, C. An Integrated Approach to Planning and Scheduling at Philips Semiconductors.[C]. in Semiconductor Manufacturing Conference Proceedings. 1997. 27-29.
[6] 童志义. 国外半导体制造设备市场[J]. 电子工业专用设备, 2005, 12: 6-9.
[7] Freed, T.C. Scheduling Semiconductor Device Test Operations[C]. in CPMT Int’l Electronics Manufacturing Technology Symposium. 1996. 482-485.
[8] Kempf, K.G. The Concepts of Chaos Applied to Manufacturing Production Scheduling[C]. in Proceedings of AAAI Workshop on Manufacturing. 1989.
[9] Kumar, P.R. Re-entrant lines[J]. Queueing Systems: Theory and Applications, Special Issue on Queueing Networks, 1993, 13: 87-110.
[10] Btazewica, J., et al. Scheduling in Computer and Manufacturing Systems. 1994: Springer-Verlag.
[11] Zhou, M.C. and M.C. Leu. Modeling and performance analysis of a flexible PCB assembly station using Petri nets[J]. Trans. ASME J. Electron. Packag., 1991, 113(4): 410-416.
[12] Xiong, H.H. Scheduling and discrete event control of flexible manufacturing systems based on Petri nets[D]. 1996, Publisher.
[13] Kim, J. and A.A. Desrochers. Modeling and analysis of semiconductor manufacturing plants using time Petri net models: COT Business Case Study[C]. in Proc. 1997 IEEE Int. Conf. Systems Man Cybern. 1997. 3227-3232.
[14] Cavalieri, S., O. Mirabella, and S. Marroccia. Improving flexible semiconductor manufacturing system performance by a colored Petri net-based scheduling algorithm[C]. in Proceedings 6th IEEE Int. Conf. Emerging Technologies and Factory Automation. Los Angeles. 1997. 369-374.
[15] Zhou, M.C. and M.D. Jeng. Modeling, Analysis, Simulation, Scheduling and control of Semiconductor Manufacturing systems: A petri net approach[J]. IEEE Transactions on Semiconductor Manufacturing, 1998, 11(3): 333-357.
[16] Choi, J.Y. and S.A. Reveliotis. A Generalized Stochastic Petri Net Model for Performance Analysis and Control of Capacitated Re-entrant lines[J]. IEEE Transactions on Robotics and Automation, 2003, 9(3): 474-480.
[17] 黄丹, et al. 基于 Petri 网的半导体生产线建模[J]. 计算机工程, 2005, 31(5): 69-72.
[18] Duenyas, I., J.W. Fowler, and L.W. Schruben. Planning and scheduling in Japanese semiconductor manufacturing[J]. Journal of manufacturing systems, 1994, 13(5): 323-332.
[19] Ohkura, M., K. Mizuno, and J. Yugami. Semiconductor process line scheduling expert system[C]. in International Symposium on semiconductor manufacturing. 1995. 89-92.
[20] Sullivan, G. and K. Fordyce. IBM Berlington's logistics management system[J]. Interfaces, 1990, 20(1): 43-64.
[21] Mittler, M. and A.K. Schoeming. Comparison of dispatching rules for semiconductor manufacuturing using large facility models[C]. in Proceedings of the 1999 winter simulation conference. 1999. 709-713.
[22] Robert Bixby, R.B., David Miller. Short-Interval Detailed Production Scheduling in 300mm Semiconductor Manufacturing using Mixed Integer and Constraint Programming[C]. in IEEE/SEMI Advanced Semiconductor Manufacturing Conference.2006. 148-154.
[23] Pierce, N.G. and T.A. Yurtsever. Value-based dispatching for semiconductor wafer fabrication[C]. in Proceedings of the international conference on modeling and analysis of semiconductor manufacturing. 2000. 172-176.
[24] Kempf, K.G. Scheduling wafer fabrication- the intelligent way[J]. SME quarterly on electronics manufacturing technology, 1989, 4(3): 1-3.
[25] Dejong, C.D. and S.P. Wu. Simulating the transport and scheduling of priority lots in semiconductor factories[C]. in Proceedings of the 2002 winter simulation conference. 2002. 1387-1891.
[26] Li, B., et al. A breakthrough in optimization throughput and manufacturing efficiency via factory-wide dynamic wip dispatching in 300mm semiconductor manufacturing[C]. in IEEE International Symposium onSemiconductor Manufacturing. 2005. 39-42.
[27] L., S.Y.Z.M.T.Y.J.Z.L.Z. Bottleneck Station Scheduling in Semiconductor Assembly and Test Manufacturing Using Ant Colony Optimization,Accepted for future publication[J]. IEEE Transactions on Automation Science and Engineering, 2007.
[28] Zaid Duwayri, M.M. Scheduling setup changes at bottleneck facilities in semiconductor manufacturing[C]. in Proceedings of the 2001 winter simulation conference. 2001. 1208-1214.
[29] Duwayri, Z.M., M.; Nazzal, D. Scheduling setup operations for bottleneck facilities in semiconductor manufacturing[C]. in World Automation Congress, 2002. Proceedings of the 5th Biannual. 2002. 109 - 114.
[30] Harrison, J.M. Brownian models of queueing networks with heterogeneous customer populations[J]. IMA volumn in mathematics and its applications, 1988, 10: 147-186.
[31] Harrison, J.M. and L.M. Wein. Scheduling networks of queues:heavy traffic analysis of a two-station closed network[J]. Operation Research, 1990, 38: 1052-1064.
[32] Wein, L.M. Scheduling networks of queues:heavy traffic analysis of a two station network with controllable inputs[J]. Operation Research, 1990, 38(6): 1065-1078.
[33] Perkins, J.R., C. Humes, and P.R. Kumar. Distributed scheduling of flexible manufacturing systems: stability and performance[J]. IEEE Transactions on Robotics and Automation, 1994, 10(2): 133-141.
[34] Kumar, S. and P.R. Kumar. Performance bounds for queueing networks and scheduling policies[J]. IEEE Transactions on Automatic Control, 1994, 39(8): 1600-1611.
[35] Morrison, J.R. and P.R. Kumar. Guaranteed efficiency in closed reentrant networks[C]. in Proceedings of the 36th conference on decision&control. San Diego. 1997. 1175-1180.
[36] Morrison, J.R. and P.R. Kumar. New performance bounds for semiconductor manufacturing plants: batch tools and setups[C]. in Proceedings of the 38th conference on Decision&control. phoenix. 1999. 1363-1367.
[37] Kumar, S. and P.R. Kumar. Queueing network models in the design and analysis of semiconductor wafer fabs[J]. IEEE Transactions on Robotics and Automation, 2001, 17: 548-561.
[38] 王中杰, et al. Brownian 模型及其在半导体生产系统中的应用概述[J]. 同济大学学报(自然科学版), 2005, 33(5): 683-686.
[39] Chen, H. and M. A. Discrete flow networks: Bottleneck analysis and fluid approximation[J]. Mathematics Operation Research, 1991, 16: 408-446.
[40] Chen, H. and D.D. Yao. A fluid model for system with random disruptions[J]. Operation Research, 1992, 40(2): 239-247.
[41] Chen, H. and D.D. Yao. Dynamic scheduling of a multiclass fluid network[J]. Operation Research, 1993, 41(6): 1104-1115.
[42] Connors, D., G. Feigin, and D.D. Yao. Scheduling semiconductor lines using a fluid network model[J]. IEEE Transactions on Robotics and Automation, 1994, 10(2): 88-98.
[43] Dai, J.G. On positive Harris recurrence of multiclass queueing networks:a fluid approach via fluid limit models[J]. Annals of Applied Probability, 1995, 5: 49-77.
[44] Dai, J.G., H.John, and V. Vate, Global stability of two-station queueing networks[M], in Stochastic networks:stability and rare events. 1996. 1-26.
[45] Chen, H. and D.D. Yao, Stable priority disiplines for multiclass networks[M], in Stochastic networks:stability and rare events. 1996. 27-40.
[46] Kumar, S. and P.R. Kumar. Fluctuation smoothing policies are stable for stochastic reentrant lines[J]. Discrete Event Dynamic Systems: Theory and applications, 1996, 6: 361-370.
[47] Huai Zhang, Z.J., Chengtao Guo, and Huiran Liu. An Extended Object-oriented PetriNets Modeling Based Simulation Platform for Real-time Scheduling of Semiconductor Wafer Fabrication System[C]. in IEEE International Conference on Systems, Man, and Cybernetics. 2006. 3411-3416.
[48] Liu, H.R., Fung, Richard Y. K.and Jiang, Z. B. Modeling of Semiconductor Wafer Fabrication Systems by Extended Object-oriented Petri Nets[J]. International Journal of Production Research, 2005, 43(3): 471-495.
[49] 李莉. 半导体生产线动态实时智能调度方法研究[D]. 2005, Publisher.
[50] 卫军胡. 半导体制造系统的仿真调度及其应用研究[D]. 2001, Publisher.
[51] Dayhoff, J.E. and R.W. Atherton. Simulation of VLSI manufacturing areas[J]. VLSI Design, 1984: 84-92.
[52] Dayhoff, J.E. and R.W. Atherton. Signature analysis of dispatch schemes in wafer fabrication[J]. IEEE Transactions on Components, Hybirds and Manufacturing Technology, 1986, 9(4): 518-525.
[53] Dayhoff, J.E. and R.W. Atherton. Signature analysis:simulation of inventory,cycle time and throughput tradeoffs in wafer fabrication[J]. IEEE Transactions on Components, Hybirds and Manufacturing Technology, 1986, 9(4): 498-507.
[54] A. K. Gupta, A.I.S. Conjunctive simulated scheduling[J]. Int. J. Adv. Manuf. Technol., 2005, 26(11–12): 1409-1413.
[55] Davis, W.J., On-line simulation: need and evolving research requirements[M], in Handbook of Simulation. 1998, John Wiley&Sons. 465-516.
[56] Davis, W.J., C. Xu, and A. Brook. Implementing on-line simulation upon the worldwide web[C]. in Proceedings of the 1998 Winter Simulation Conference. 1998. 87-95.
[57] Sivakumar, A.I. Optimization of cycle time and utilization in semiconductor test manufacutring using simulation based, on-line, near-real-time scheduling system[C]. in Proceedings of the 1999 winter simulation conference. 1999. 727-735.
[58] Thiel, M., R. Schulz, and P. Gmilkowsky. Simulation based production control in the semiconductor industry[C]. in Proceedings of the 1998 winter simulation conference. 1998. 1029-1033.
[59] Rippenhagen, C. and S. Krishnaswamy. Implementing the theory of constraints philosophy in highly reentrant systems[C]. in Proceedings of the 1998 winter simulation conference. 1998. 993-996.
[60] Watt, D.G. Integrating simulation based scheduling with MES in a semiconductor FAB[C]. in Proceedings of the 1998 winter simulation conference. 1998. 1713-1715.
[61] Hsieh, B.W., C.H. Chen, and S.C. Chang. Scheduling Semiconductor Wafer Fabrication by Using Ordinal Optimization-Based Simulation[J]. IEEE Transactions on Robotics and Automation, 2001, 17(5): 599-608.
[62] Kim, Y.-D., et al. Simplification Methods for Accelerating Simulation-Based Real-Time Scheduling in a Semiconductor Wafer Fabrication Facility[J]. IEEE Transactions on Semiconductor Manufacturing, 2003, 16(2): 290-298.
[63] Kuhl, M.E. and G.R. Laubisch. A Simulation Study of Dispatching and Rework Strategies in Semiconductor Manufacturing[C]. in SEMI Advanced Semiconductor Manufacturing Conferece. 2004. 325-329.
[64] Arisha, A. and P. Young. Intelligent Simulation-based Lot Scheduling of Photolithography Toolsets in a Wafer Fabrication Facility[C]. in Proceedings of the 2004 Winter Simulation Conference. 2004. 1935-1942.
[65] Appa Iyer Sivakumar, A.K.G. Online Multiobjective Pareto Optimal Dynamic Scheduling of Semiconductor Back-End Using Conjunctive Simulated Scheduling[J]. IEEE Transactions ON Eletronics Packaging Manufacturing, 2006, 29(2): 99-109.
[66] A. K. Gupta, A.l.S. Simulation based multiobjective schedule optimization in semiconductor manufacturing[C]. in Proceedings of the 2002 Winter simulation conference. 2002. 1862-1870.
[67] Uzsoy, R., C.Y. LEE, and L.A. Martin-Vega. A review of production planning and scheduling models in the semiconductor inductory part II: shop floor control[J]. IIE Transactions, 1994, 26(5): 44-55.
[68] Wein, L.M. Scheduling semiconductor wafer fabrication[J]. IEEE Transactions on Semiconductor Manufacturing, 1988, 1(3): 115-129.
[69] Glassey, C.R. and M.G.C. Resende. Closed-loop job release control for VLSI circuit manufacturing[J]. IEEE Transactions on Semiconductor Manufacturing, 1988, 1(1): 36-46.
[70] Leachman, R.C., M. Solorzano, and C.R. Glassey. A queue management policy forrelease of factory work orders[J]. Journal of Manufacturing Operation Management, 1988.
[71] Lu, S.H. and P.R. Kumar. Distributed scheduling based on due dates and buffer priorities[J]. IEEE Transactions on Automatic Control, 1991, 36(12): 1406-1416.
[72] Narahari, Y. and L.M. Khan. Asymptotic loss of priority scheduling policies in closed re-entrant lines: a computer study[J]. European journal of operation research, 1998, 110: 585-596.
[73] Lin, C., et al. A Sufficient Condition for Instability of Buffer Priority Policies in Re-Entrant Lines[J]. IEEE Transactions on Automatic Control, 2003, 48(7): 1235-1238.
[74] Chik, M., I. Ahmad, and M. Jamaluddin. A simulation approach for dispatching techniques comparison in 200mm wafer foundry[C]. in ICSE 2004. 2004. 645-649.
[75] Liao, D.Y., S.C. Chang, and S.R. Yen. Daily scheduling for R&D semiconductor fabrication[C]. in Proceedings of IEEE Conference on Robotics and Automation. 1993. 77-83.
[76] Liao, D.Y., S.C. Chang, and K.W. Pei. Daily scheduling for R&D semiconductor fabrication[J]. IEEE Transactions on Semiconductor Manufacturing, 1996, 9(4): 550-561.
[77] Hwang, T.K. and S.C. Chang. Design of a lagrangian relaxation-based hierarchical production scheduling environment for semiconductor wafer fabrication[J]. IEEE Transactions on Robotics and Automation, 2003, 19(4): 566-578.
[78] Shen, Y.X. and R.C. Leachman. Stochastic wafer fabrication sheduling[J]. IEEE Transactions on Semiconductor Manufacturing, 2003, 16(1): 2-14.
[79] Yoon, H.J. and D.Y. Lee. Online Scheduling of Integrated Single-Wafer Processing Tools With Temporal Constraints[J]. IEEE Transactions on Semiconductor Manufacturing, 2005, 18(4): 390-398.
[80] Bertsimas, D., I.C. Paschalidis, and J.N. Tsitsiklis. Scheduling of multiclass networks: bounds on achievable performance[C]. in Workshop on hierarchical control for real-time scheduling of manufacturing systems. 1992. 16-18.
[81] Bertsimas, D., I.C. Paschalidis, and J.N. Tsitsiklis. Optimization of multiclass queueing networks: polyhedral nonlinear characterizations of achievable performance. 1992: MIT.
[82] Kumar, P.R. and S.P. Meyn. Duality and linear programs for stability and performance analysis of queueing networks and scheduling policies[J]. IEEE Transactions on Automatic Control, 1996, 41(1): 4-17.
[83] Morrison, J.R. and P.R. Kumar. On the guaranteed throughput and efficiency of closed re-entrant lines[J]. Queueing Systems: Theory and Applications, Special Issue on Queueing Networks, 1998, 28: 33-54.
[84] Morrison, J.R. and P.R. Kumar. New linear program performance bounds for queueing netwoks[J]. Journal of optimization theory and applications, 1999, 100: 575-597.
[85] Morrison, J.R. and P.R. Kumar. New linear program performance bounds for closed queueing networks[J]. Discrete Event Dynamic Systems:Theory and applications, 2001, 11: 291-317.
[86] Fox, M.S. and S.F. Smith. ISIS A Knowledge-based system for factory scheduling[J]. Expert systems, 1984, 1: 25-49.
[87] Fox, M.S., ISIS: A retrospective[M], in Intelligent Scheduling, M. Zweben and M.S. Fox, Editors. 1994.
[88] Kempf, K.G., C.D. Pape, and S.F. Smith. Issues in the design of artificially intelligent schudulers[J]. AI Magzine, 1991, 11(5): 37-45.
[89] Ellen, S.D., R. Liquigan, and B.A. Peters. Development of an intelligent scheduler for semiconductor manufacturing facilities[C]. in SEMI Advanced semiconductor manufacturing conference. 1995. 159-162.
[90] Savell, D., R. Perez, and S. Koh. Scheduling semiconductor wafer production: an expert system implementation[J]. IEEE Expert, 1989, 6(3): 9-15.
[91] Roobeek, F. A better choice-a fuzzy logic based lot sequencing decision support system for operators in a job shop fab with reentrant process flows[C]. in Proceedings of the 1997 IEEE International symposium on semiconductor on manufacturing conference. 1997. 245-251.
[92] 王然 and 吴澄. 智能规则在半导体生产线调度中的应用[J]. 计算机集成制造系统, 1997, 20(4): 833-835.
[93] Cigolini, R. and A. Micheletti. Implementing new dispatching rules at SGS-Thomson microelectronics[J]. Production planning and control, 1999, 10(1): 97-106.
[94] Dabbas, R.M. A new scheduling approach using combined dispatching criteria insemiconductor manufacturing systems[D]. 1999, Publisher.
[95] R. M. Dabbas, H.N.C., J. W. Fowler. A combined dispatching criteria approach to scheduling semiconductor manufacturing systems[J]. Computers & Industrial Engineering, 2001, 39(3-4): 307-324.
[96] R. M. Dabbas, J.W.F., D. A. Rollier. Multiple response optimization using mixture-designed experiments and desirability functions in semiconductor scheduling[J]. International Journal of Production Research, 2003, 41(5): 939-961.
[97] Fowler, R.M.D.a.J.W. A new scheduling approach using combined dispatching criteria in wafer fabs[J]. IEEE Transactions on Semiconductor Manufacturing, 2003, 16 (3): 501-510.
[98] Hsieh, B.W., S.C. Chang, and H.N. Chen. Dynamic scheduling rule selection for semiconductor wafer fabrication[C]. in International conference on robotics and automation. 2001. 535-540.
[99] Duwayri, Z., M. Mollaghasemi, and D. Nazzal. Scheduling setup changes at bottleneck facilities in semiconductor manufacturing[C]. in Proceedings of the 2001 winter simulation conference. 2001. 1208-1214.
[100] Habenicht, I. and L. Monch. A finite-capacity beam-search-algorithm for production scheduling in semiconductor manufacturing[C]. in Proceedings of the 2002 winter simulation conference. 2002. 1406-1413.
[101] 王中杰, 吴启迪, and 有杰. 基于多目标的半导体生产线满意调度[J]. 控制与决策, 2002, 17(6): 856-859.
[102] Zhongjie Wang, Q.W. Multi-object optimal scheduling for semiconductor manufacturing line based on satisfactory control[C]. in Proceedings of the American Control Conference. 2002. 1603-1608.
[103] 梁韡. 基于滑动窗口机制的动态调度问题研究[D]. 2002, Publisher.
[104] Dabbas, R.M. and J.W. Fowler. A New Scheduling Approach Using Combined Dispatching Criteria in Wafer Fabs[J]. IEEE Transactions on Semiconductor Manufacturing, 2003, 16(3): 501-510.
[105] 吴继伟 and 萧韵诗. 多智能体在半导体生产线调度中的应用[J]. 计算机集成制造系统, 2003, 9(8): 641-644.
[106] Li, L., F. Qiao, and Q. Wu. Agent-based dynamic scheduling for semiconductor wafer fab[C]. in IEEE International conference on networking, sensing and control. 2005. 163-168.
[107] Li, L., et al. The research on dispatching rule for improving on-time delivery for semiconductor wafer fab[C]. in International conference on control, automation, robotics and vision. 2004. 494-498.
[108] 王遵彤, 乔非, and 吴启迪. 半导体硅片加工过程复合控制策略研究及仿真[J]. 系 统 仿 真 学 报, 2005, 17(8): 1924-1928.
[109] 王遵彤, 乔非, and 吴启迪. 基于 CBR 的半导体生产线组合调度策略研究[J]. 计算机工程, 2005, 31(7): 183-185.
[110] Nose, K. and A. Konishi. Using genetic algorithm for job-shop scheduling problems with reentrant production flows[C]. in ETFA proceedings of the IEEE international conference on emerging technologies and factory automation. 1999. 241-246.
[111] Liu, M. and C. Wu. Genetic algorithm using sequence rule chain for multi-objective optimization in re-entrant micro-electronic production line[J]. Robotics and computer-integrated manufacturing, 2004, 20(3): 225-236.
[112] 吕文彦 and 党延忠. 基于 B-T 规则与遗传算法的可重入生产系统调度[J]. 系统仿真学报, 2005, 17(4): 993-996.
[113] Jiang, H., et al. The new method of dynamic scheduling in semiconductor fabrication line[C]. in International conference on control, automation, robotics and vision. 2004. 1874-1878.
[114] Koole, G. and A. Pot. Workload Minimization in Re-entrant Lines[J]. European Journal of operation research, 2006, 174: 216-233.
[115] Choi, J.Y. and S.A. Reveliotis. Relative value function approximation for the capacitated re-entrant line scheduling problem[J]. IEEE Transactions on automation science and engineering, 2005, 2(3): 285-299.
[116] 王利存 and 郑应平. 可重入生产系统的递阶增强型学习调度[J]. 信息与控制, 2001, 30(3): 199-203.
[117] Kumar, P.R. Efficient scheduling policies to reduce mean and variance of cycle-time insemiconductor manufactuing plants[J]. IEEE Transactions on Semiconductor Manufacturing, 1994, 7(3): 374-388.
[118] 王颖,朱顺痣,许威,缪克华,李茂青. 基于神经元动态规划的可重入生产系统调度的仿真框架[J]. 信息与控制, 2007, 36(2): 218-223.
[119] Bertsekas, D.P. and J.N. Tsitsiklis. Neuro-dynamic programming. 1996: Athena scientific.
[120] 殷保群. 排队系统性能分析与 Markov 控制过程. 中国科学技术大学出版社, 2003, 合肥.
[121] Lu, S.H., D. Ramaswamy, and P.R. Kumar. Efficient scheduling policies to reduce mean and variance of cycle-time in semiconductor manufacturing plants[J]. IEEE Transactions on Semiconductor Manufacturing, 1994, 7(3): 374-385.
[122] Puterman,M.L., Markov decision process discrete stochastic dynamic programming[M]. 2005, New Jersey: John Wiley&Sons.
[123] Bertsekas, D.P. and J.N. Tsitsiklis, Neuro-Dynamic Programming: An Overview[C]. Conference on Decision and Control. 1995.
[124] 何毓琦, 优化——光彩夺目的世界[M]. 1999: 西安交通大学出版社.
[125] Minsky, M.L., Theory of neural analog reinforcement system and its application to the brain model problem[M]. 1954, New Jersey: USA Princeton Univ.
[126] Sutton, R.S., Learning to Predict by the Methods of Temporal Difference[J]. Machine learning, 1988. 3:9-44.
[127] Cichosz, P., Truncating temporal differences: on the efficient implementation of TD for reinforcement learning[J]. Artificial Intelligence Research, 1996.12:287-318.
[128] Dayan, P., The convergence of TD(λ) for general λ[J]. Machine learning, 1992. 8: 341-362.
[129] Badtke, S.J. and R.G. Barto, Linear least squares algorithms for temporal difference Learning[J]. Machine learning, 1996.22:33-57.
[130] Yu, H. and D.P. Bertsekas, Convergence Results for Some Temporal Difference Methods Based on Least Squares[Z]. 2006, LIDS-2697.
[131] Bertsekas, D.P., Improved Temporal Difference Methods with Linear Function Approximation[Z]. 2003, LIDS-2573.
[132] Watkins, J.C., Learning from delayed rewards[D]. 1989, Cambridge.
[133] Watkins, J.C. and P. Dayan, Q-learning[J]. Machine learning, 1992.8:279-292.
[134] Tesauro, G.J., Issues on temporal difference learning[J]. Machine learning, 1992. 8:257-277.
[135] Zhang, W. A reinforcement learning approach to job shop scheduling[C]. 14th IJCAI.,1995
[136] Roy, B.V., D. Bertsimas, and J.N. Tsitsiklis. A neuro-dynamic programming approach to retailer inventory management[C]. 36th Conference on decision and control. 1997: 4052-4057.
[137] Marbach, P. and J.N. Tsitsiklis, A neuro-dynamic programming approach to admission control in ATM networks: the single link case[Z]. 1997, LIDS-2402.
[138] Crites, R.H. and A.G. Barto,. Improving elevator performance using reinforcement learning [J]. Advances in Neural Information Processing Systems, 1996,8:1017-1023.
[139] Singh, S. and D.Bertsekas, Reinforcement learning for dynamic channel allocation in cellular telephone systems[Z]. Advances in Neural Information Processing Systems.1997,9:974-980.
[140] Nie, J. and S. Haykin, A Q-learning-based dynamic channel assignment technique for mobile communication systems[J]. IEEE Transactions on Vehicular Technology, 1998,45(5):1676～1687.
[141] Nie, J. and S. Haykin, A dynamic channel assignment policy through Q-learning[R], in CRL Report NO.334. 1996, Communications research laboratory, McMaster University, Hamilton, Ontario.
[142] Bertsekas, D.P., et al., Mission defence and interceptor allocation by neuro-dynamic programming[J]. IEEE Transactions on systems, man and cybernetics, 2000. 30(1): 42-51.
[143] D.Bertsekas, 动态规划:确定性和随机性模型[M], ed. 李人厚,韩崇昭译. 1988, 西安: 西安交通大学出版社.
[144] 张有为, 动态规划[M]. 1991, 湖南: 湖南科学技术出版社.
[145] 金辉宇, 神经元动态规划在可重入生产系统调度中的应用[D]. 2001, 中国科学院沈阳自动化研究所.
[146] Choi, J.Y., Performance Modeling, Analysis and Control of capacitated re-entrant lines[D].2004, Georgia Institute of Technology.
[147] Kumar, P.R., Scheduling manufacturing systems for re-entrant lines[C], Stochastic modeling and analysis of manufacturing systems. 1994, 325-360.
[148] Lu, S.H., D. Ramaswamy, and P.R. Kumar, Efficient scheduling policies to reduce mean and variance of cycle-time in semiconductor manufacturing plants[J]. IEEE Transactions on Semiconductor Manufacturing, 1994. 7(3): 374-385.
[2] Leachman, R.C. and D.A. Hodges. Benchmarking Semiconductor Manufacturing[J]. IEEE Transactions on Semiconductor Manufacturing, 1996, 9(2): 158-169.
[3] Pickett, B. and M. Zuniga. Modeling, scheduling, and dispatching in the dynamic environment of semiconductor manufacturing at FASL, Japan[C]. in SEMI Advanced semiconductor manufacturing conference. 1997. 448-450.
[4] Potoradi, J., S.J. Mason, and J.W. Fowler. Using Simulation-based Scheduling to Maximize Demand Fulfillment in a Semiconductor Assembly Facility[C]. in Proceedings of the 2002 Winter Simulation Conference. 2002. 1857-1861.
[5] Malmstrom, C. An Integrated Approach to Planning and Scheduling at Philips Semiconductors.[C]. in Semiconductor Manufacturing Conference Proceedings. 1997. 27-29.
[6] 童志义. 国外半导体制造设备市场[J]. 电子工业专用设备, 2005, 12: 6-9.
[7] Freed, T.C. Scheduling Semiconductor Device Test Operations[C]. in CPMT Int’l Electronics Manufacturing Technology Symposium. 1996. 482-485.
[8] Kempf, K.G. The Concepts of Chaos Applied to Manufacturing Production Scheduling[C]. in Proceedings of AAAI Workshop on Manufacturing. 1989.
[9] Kumar, P.R. Re-entrant lines[J]. Queueing Systems: Theory and Applications, Special Issue on Queueing Networks, 1993, 13: 87-110.
[10] Btazewica, J., et al. Scheduling in Computer and Manufacturing Systems. 1994: Springer-Verlag.
[11] Zhou, M.C. and M.C. Leu. Modeling and performance analysis of a flexible PCB assembly station using Petri nets[J]. Trans. ASME J. Electron. Packag., 1991, 113(4): 410-416.
[12] Xiong, H.H. Scheduling and discrete event control of flexible manufacturing systems based on Petri nets[D]. 1996, Publisher.
[13] Kim, J. and A.A. Desrochers. Modeling and analysis of semiconductor manufacturing plants using time Petri net models: COT Business Case Study[C]. in Proc. 1997 IEEE Int. Conf. Systems Man Cybern. 1997. 3227-3232.
[14] Cavalieri, S., O. Mirabella, and S. Marroccia. Improving flexible semiconductor manufacturing system performance by a colored Petri net-based scheduling algorithm[C]. in Proceedings 6th IEEE Int. Conf. Emerging Technologies and Factory Automation. Los Angeles. 1997. 369-374.
[15] Zhou, M.C. and M.D. Jeng. Modeling, Analysis, Simulation, Scheduling and control of Semiconductor Manufacturing systems: A petri net approach[J]. IEEE Transactions on Semiconductor Manufacturing, 1998, 11(3): 333-357.
[16] Choi, J.Y. and S.A. Reveliotis. A Generalized Stochastic Petri Net Model for Performance Analysis and Control of Capacitated Re-entrant lines[J]. IEEE Transactions on Robotics and Automation, 2003, 9(3): 474-480.
[17] 黄丹, et al. 基于 Petri 网的半导体生产线建模[J]. 计算机工程, 2005, 31(5): 69-72.
[18] Duenyas, I., J.W. Fowler, and L.W. Schruben. Planning and scheduling in Japanese semiconductor manufacturing[J]. Journal of manufacturing systems, 1994, 13(5): 323-332.
[19] Ohkura, M., K. Mizuno, and J. Yugami. Semiconductor process line scheduling expert system[C]. in International Symposium on semiconductor manufacturing. 1995. 89-92.
[20] Sullivan, G. and K. Fordyce. IBM Berlington's logistics management system[J]. Interfaces, 1990, 20(1): 43-64.
[21] Mittler, M. and A.K. Schoeming. Comparison of dispatching rules for semiconductor manufacuturing using large facility models[C]. in Proceedings of the 1999 winter simulation conference. 1999. 709-713.
[22] Robert Bixby, R.B., David Miller. Short-Interval Detailed Production Scheduling in 300mm Semiconductor Manufacturing using Mixed Integer and Constraint Programming[C]. in IEEE/SEMI Advanced Semiconductor Manufacturing Conference.2006. 148-154.
[23] Pierce, N.G. and T.A. Yurtsever. Value-based dispatching for semiconductor wafer fabrication[C]. in Proceedings of the international conference on modeling and analysis of semiconductor manufacturing. 2000. 172-176.
[24] Kempf, K.G. Scheduling wafer fabrication- the intelligent way[J]. SME quarterly on electronics manufacturing technology, 1989, 4(3): 1-3.
[25] Dejong, C.D. and S.P. Wu. Simulating the transport and scheduling of priority lots in semiconductor factories[C]. in Proceedings of the 2002 winter simulation conference. 2002. 1387-1891.
[26] Li, B., et al. A breakthrough in optimization throughput and manufacturing efficiency via factory-wide dynamic wip dispatching in 300mm semiconductor manufacturing[C]. in IEEE International Symposium onSemiconductor Manufacturing. 2005. 39-42.
[27] L., S.Y.Z.M.T.Y.J.Z.L.Z. Bottleneck Station Scheduling in Semiconductor Assembly and Test Manufacturing Using Ant Colony Optimization,Accepted for future publication[J]. IEEE Transactions on Automation Science and Engineering, 2007.
[28] Zaid Duwayri, M.M. Scheduling setup changes at bottleneck facilities in semiconductor manufacturing[C]. in Proceedings of the 2001 winter simulation conference. 2001. 1208-1214.
[29] Duwayri, Z.M., M.; Nazzal, D. Scheduling setup operations for bottleneck facilities in semiconductor manufacturing[C]. in World Automation Congress, 2002. Proceedings of the 5th Biannual. 2002. 109 - 114.
[30] Harrison, J.M. Brownian models of queueing networks with heterogeneous customer populations[J]. IMA volumn in mathematics and its applications, 1988, 10: 147-186.
[31] Harrison, J.M. and L.M. Wein. Scheduling networks of queues:heavy traffic analysis of a two-station closed network[J]. Operation Research, 1990, 38: 1052-1064.
[32] Wein, L.M. Scheduling networks of queues:heavy traffic analysis of a two station network with controllable inputs[J]. Operation Research, 1990, 38(6): 1065-1078.
[33] Perkins, J.R., C. Humes, and P.R. Kumar. Distributed scheduling of flexible manufacturing systems: stability and performance[J]. IEEE Transactions on Robotics and Automation, 1994, 10(2): 133-141.
[34] Kumar, S. and P.R. Kumar. Performance bounds for queueing networks and scheduling policies[J]. IEEE Transactions on Automatic Control, 1994, 39(8): 1600-1611.
[35] Morrison, J.R. and P.R. Kumar. Guaranteed efficiency in closed reentrant networks[C]. in Proceedings of the 36th conference on decision&control. San Diego. 1997. 1175-1180.
[36] Morrison, J.R. and P.R. Kumar. New performance bounds for semiconductor manufacturing plants: batch tools and setups[C]. in Proceedings of the 38th conference on Decision&control. phoenix. 1999. 1363-1367.
[37] Kumar, S. and P.R. Kumar. Queueing network models in the design and analysis of semiconductor wafer fabs[J]. IEEE Transactions on Robotics and Automation, 2001, 17: 548-561.
[38] 王中杰, et al. Brownian 模型及其在半导体生产系统中的应用概述[J]. 同济大学学报(自然科学版), 2005, 33(5): 683-686.
[39] Chen, H. and M. A. Discrete flow networks: Bottleneck analysis and fluid approximation[J]. Mathematics Operation Research, 1991, 16: 408-446.
[40] Chen, H. and D.D. Yao. A fluid model for system with random disruptions[J]. Operation Research, 1992, 40(2): 239-247.
[41] Chen, H. and D.D. Yao. Dynamic scheduling of a multiclass fluid network[J]. Operation Research, 1993, 41(6): 1104-1115.
[42] Connors, D., G. Feigin, and D.D. Yao. Scheduling semiconductor lines using a fluid network model[J]. IEEE Transactions on Robotics and Automation, 1994, 10(2): 88-98.
[43] Dai, J.G. On positive Harris recurrence of multiclass queueing networks:a fluid approach via fluid limit models[J]. Annals of Applied Probability, 1995, 5: 49-77.
[44] Dai, J.G., H.John, and V. Vate, Global stability of two-station queueing networks[M], in Stochastic networks:stability and rare events. 1996. 1-26.
[45] Chen, H. and D.D. Yao, Stable priority disiplines for multiclass networks[M], in Stochastic networks:stability and rare events. 1996. 27-40.
[46] Kumar, S. and P.R. Kumar. Fluctuation smoothing policies are stable for stochastic reentrant lines[J]. Discrete Event Dynamic Systems: Theory and applications, 1996, 6: 361-370.
[47] Huai Zhang, Z.J., Chengtao Guo, and Huiran Liu. An Extended Object-oriented PetriNets Modeling Based Simulation Platform for Real-time Scheduling of Semiconductor Wafer Fabrication System[C]. in IEEE International Conference on Systems, Man, and Cybernetics. 2006. 3411-3416.
[48] Liu, H.R., Fung, Richard Y. K.and Jiang, Z. B. Modeling of Semiconductor Wafer Fabrication Systems by Extended Object-oriented Petri Nets[J]. International Journal of Production Research, 2005, 43(3): 471-495.
[49] 李莉. 半导体生产线动态实时智能调度方法研究[D]. 2005, Publisher.
[50] 卫军胡. 半导体制造系统的仿真调度及其应用研究[D]. 2001, Publisher.
[51] Dayhoff, J.E. and R.W. Atherton. Simulation of VLSI manufacturing areas[J]. VLSI Design, 1984: 84-92.
[52] Dayhoff, J.E. and R.W. Atherton. Signature analysis of dispatch schemes in wafer fabrication[J]. IEEE Transactions on Components, Hybirds and Manufacturing Technology, 1986, 9(4): 518-525.
[53] Dayhoff, J.E. and R.W. Atherton. Signature analysis:simulation of inventory,cycle time and throughput tradeoffs in wafer fabrication[J]. IEEE Transactions on Components, Hybirds and Manufacturing Technology, 1986, 9(4): 498-507.
[54] A. K. Gupta, A.I.S. Conjunctive simulated scheduling[J]. Int. J. Adv. Manuf. Technol., 2005, 26(11–12): 1409-1413.
[55] Davis, W.J., On-line simulation: need and evolving research requirements[M], in Handbook of Simulation. 1998, John Wiley&Sons. 465-516.
[56] Davis, W.J., C. Xu, and A. Brook. Implementing on-line simulation upon the worldwide web[C]. in Proceedings of the 1998 Winter Simulation Conference. 1998. 87-95.
[57] Sivakumar, A.I. Optimization of cycle time and utilization in semiconductor test manufacutring using simulation based, on-line, near-real-time scheduling system[C]. in Proceedings of the 1999 winter simulation conference. 1999. 727-735.
[58] Thiel, M., R. Schulz, and P. Gmilkowsky. Simulation based production control in the semiconductor industry[C]. in Proceedings of the 1998 winter simulation conference. 1998. 1029-1033.
[59] Rippenhagen, C. and S. Krishnaswamy. Implementing the theory of constraints philosophy in highly reentrant systems[C]. in Proceedings of the 1998 winter simulation conference. 1998. 993-996.
[60] Watt, D.G. Integrating simulation based scheduling with MES in a semiconductor FAB[C]. in Proceedings of the 1998 winter simulation conference. 1998. 1713-1715.
[61] Hsieh, B.W., C.H. Chen, and S.C. Chang. Scheduling Semiconductor Wafer Fabrication by Using Ordinal Optimization-Based Simulation[J]. IEEE Transactions on Robotics and Automation, 2001, 17(5): 599-608.
[62] Kim, Y.-D., et al. Simplification Methods for Accelerating Simulation-Based Real-Time Scheduling in a Semiconductor Wafer Fabrication Facility[J]. IEEE Transactions on Semiconductor Manufacturing, 2003, 16(2): 290-298.
[63] Kuhl, M.E. and G.R. Laubisch. A Simulation Study of Dispatching and Rework Strategies in Semiconductor Manufacturing[C]. in SEMI Advanced Semiconductor Manufacturing Conferece. 2004. 325-329.
[64] Arisha, A. and P. Young. Intelligent Simulation-based Lot Scheduling of Photolithography Toolsets in a Wafer Fabrication Facility[C]. in Proceedings of the 2004 Winter Simulation Conference. 2004. 1935-1942.
[65] Appa Iyer Sivakumar, A.K.G. Online Multiobjective Pareto Optimal Dynamic Scheduling of Semiconductor Back-End Using Conjunctive Simulated Scheduling[J]. IEEE Transactions ON Eletronics Packaging Manufacturing, 2006, 29(2): 99-109.
[66] A. K. Gupta, A.l.S. Simulation based multiobjective schedule optimization in semiconductor manufacturing[C]. in Proceedings of the 2002 Winter simulation conference. 2002. 1862-1870.
[67] Uzsoy, R., C.Y. LEE, and L.A. Martin-Vega. A review of production planning and scheduling models in the semiconductor inductory part II: shop floor control[J]. IIE Transactions, 1994, 26(5): 44-55.
[68] Wein, L.M. Scheduling semiconductor wafer fabrication[J]. IEEE Transactions on Semiconductor Manufacturing, 1988, 1(3): 115-129.
[69] Glassey, C.R. and M.G.C. Resende. Closed-loop job release control for VLSI circuit manufacturing[J]. IEEE Transactions on Semiconductor Manufacturing, 1988, 1(1): 36-46.
[70] Leachman, R.C., M. Solorzano, and C.R. Glassey. A queue management policy forrelease of factory work orders[J]. Journal of Manufacturing Operation Management, 1988.
[71] Lu, S.H. and P.R. Kumar. Distributed scheduling based on due dates and buffer priorities[J]. IEEE Transactions on Automatic Control, 1991, 36(12): 1406-1416.
[72] Narahari, Y. and L.M. Khan. Asymptotic loss of priority scheduling policies in closed re-entrant lines: a computer study[J]. European journal of operation research, 1998, 110: 585-596.
[73] Lin, C., et al. A Sufficient Condition for Instability of Buffer Priority Policies in Re-Entrant Lines[J]. IEEE Transactions on Automatic Control, 2003, 48(7): 1235-1238.
[74] Chik, M., I. Ahmad, and M. Jamaluddin. A simulation approach for dispatching techniques comparison in 200mm wafer foundry[C]. in ICSE 2004. 2004. 645-649.
[75] Liao, D.Y., S.C. Chang, and S.R. Yen. Daily scheduling for R&D semiconductor fabrication[C]. in Proceedings of IEEE Conference on Robotics and Automation. 1993. 77-83.
[76] Liao, D.Y., S.C. Chang, and K.W. Pei. Daily scheduling for R&D semiconductor fabrication[J]. IEEE Transactions on Semiconductor Manufacturing, 1996, 9(4): 550-561.
[77] Hwang, T.K. and S.C. Chang. Design of a lagrangian relaxation-based hierarchical production scheduling environment for semiconductor wafer fabrication[J]. IEEE Transactions on Robotics and Automation, 2003, 19(4): 566-578.
[78] Shen, Y.X. and R.C. Leachman. Stochastic wafer fabrication sheduling[J]. IEEE Transactions on Semiconductor Manufacturing, 2003, 16(1): 2-14.
[79] Yoon, H.J. and D.Y. Lee. Online Scheduling of Integrated Single-Wafer Processing Tools With Temporal Constraints[J]. IEEE Transactions on Semiconductor Manufacturing, 2005, 18(4): 390-398.
[80] Bertsimas, D., I.C. Paschalidis, and J.N. Tsitsiklis. Scheduling of multiclass networks: bounds on achievable performance[C]. in Workshop on hierarchical control for real-time scheduling of manufacturing systems. 1992. 16-18.
[81] Bertsimas, D., I.C. Paschalidis, and J.N. Tsitsiklis. Optimization of multiclass queueing networks: polyhedral nonlinear characterizations of achievable performance. 1992: MIT.
[82] Kumar, P.R. and S.P. Meyn. Duality and linear programs for stability and performance analysis of queueing networks and scheduling policies[J]. IEEE Transactions on Automatic Control, 1996, 41(1): 4-17.
[83] Morrison, J.R. and P.R. Kumar. On the guaranteed throughput and efficiency of closed re-entrant lines[J]. Queueing Systems: Theory and Applications, Special Issue on Queueing Networks, 1998, 28: 33-54.
[84] Morrison, J.R. and P.R. Kumar. New linear program performance bounds for queueing netwoks[J]. Journal of optimization theory and applications, 1999, 100: 575-597.
[85] Morrison, J.R. and P.R. Kumar. New linear program performance bounds for closed queueing networks[J]. Discrete Event Dynamic Systems:Theory and applications, 2001, 11: 291-317.
[86] Fox, M.S. and S.F. Smith. ISIS A Knowledge-based system for factory scheduling[J]. Expert systems, 1984, 1: 25-49.
[87] Fox, M.S., ISIS: A retrospective[M], in Intelligent Scheduling, M. Zweben and M.S. Fox, Editors. 1994.
[88] Kempf, K.G., C.D. Pape, and S.F. Smith. Issues in the design of artificially intelligent schudulers[J]. AI Magzine, 1991, 11(5): 37-45.
[89] Ellen, S.D., R. Liquigan, and B.A. Peters. Development of an intelligent scheduler for semiconductor manufacturing facilities[C]. in SEMI Advanced semiconductor manufacturing conference. 1995. 159-162.
[90] Savell, D., R. Perez, and S. Koh. Scheduling semiconductor wafer production: an expert system implementation[J]. IEEE Expert, 1989, 6(3): 9-15.
[91] Roobeek, F. A better choice-a fuzzy logic based lot sequencing decision support system for operators in a job shop fab with reentrant process flows[C]. in Proceedings of the 1997 IEEE International symposium on semiconductor on manufacturing conference. 1997. 245-251.
[92] 王然 and 吴澄. 智能规则在半导体生产线调度中的应用[J]. 计算机集成制造系统, 1997, 20(4): 833-835.
[93] Cigolini, R. and A. Micheletti. Implementing new dispatching rules at SGS-Thomson microelectronics[J]. Production planning and control, 1999, 10(1): 97-106.
[94] Dabbas, R.M. A new scheduling approach using combined dispatching criteria insemiconductor manufacturing systems[D]. 1999, Publisher.
[95] R. M. Dabbas, H.N.C., J. W. Fowler. A combined dispatching criteria approach to scheduling semiconductor manufacturing systems[J]. Computers & Industrial Engineering, 2001, 39(3-4): 307-324.
[96] R. M. Dabbas, J.W.F., D. A. Rollier. Multiple response optimization using mixture-designed experiments and desirability functions in semiconductor scheduling[J]. International Journal of Production Research, 2003, 41(5): 939-961.
[97] Fowler, R.M.D.a.J.W. A new scheduling approach using combined dispatching criteria in wafer fabs[J]. IEEE Transactions on Semiconductor Manufacturing, 2003, 16 (3): 501-510.
[98] Hsieh, B.W., S.C. Chang, and H.N. Chen. Dynamic scheduling rule selection for semiconductor wafer fabrication[C]. in International conference on robotics and automation. 2001. 535-540.
[99] Duwayri, Z., M. Mollaghasemi, and D. Nazzal. Scheduling setup changes at bottleneck facilities in semiconductor manufacturing[C]. in Proceedings of the 2001 winter simulation conference. 2001. 1208-1214.
[100] Habenicht, I. and L. Monch. A finite-capacity beam-search-algorithm for production scheduling in semiconductor manufacturing[C]. in Proceedings of the 2002 winter simulation conference. 2002. 1406-1413.
[101] 王中杰, 吴启迪, and 有杰. 基于多目标的半导体生产线满意调度[J]. 控制与决策, 2002, 17(6): 856-859.
[102] Zhongjie Wang, Q.W. Multi-object optimal scheduling for semiconductor manufacturing line based on satisfactory control[C]. in Proceedings of the American Control Conference. 2002. 1603-1608.
[103] 梁韡. 基于滑动窗口机制的动态调度问题研究[D]. 2002, Publisher.
[104] Dabbas, R.M. and J.W. Fowler. A New Scheduling Approach Using Combined Dispatching Criteria in Wafer Fabs[J]. IEEE Transactions on Semiconductor Manufacturing, 2003, 16(3): 501-510.
[105] 吴继伟 and 萧韵诗. 多智能体在半导体生产线调度中的应用[J]. 计算机集成制造系统, 2003, 9(8): 641-644.
[106] Li, L., F. Qiao, and Q. Wu. Agent-based dynamic scheduling for semiconductor wafer fab[C]. in IEEE International conference on networking, sensing and control. 2005. 163-168.
[107] Li, L., et al. The research on dispatching rule for improving on-time delivery for semiconductor wafer fab[C]. in International conference on control, automation, robotics and vision. 2004. 494-498.
[108] 王遵彤, 乔非, and 吴启迪. 半导体硅片加工过程复合控制策略研究及仿真[J]. 系 统 仿 真 学 报, 2005, 17(8): 1924-1928.
[109] 王遵彤, 乔非, and 吴启迪. 基于 CBR 的半导体生产线组合调度策略研究[J]. 计算机工程, 2005, 31(7): 183-185.
[110] Nose, K. and A. Konishi. Using genetic algorithm for job-shop scheduling problems with reentrant production flows[C]. in ETFA proceedings of the IEEE international conference on emerging technologies and factory automation. 1999. 241-246.
[111] Liu, M. and C. Wu. Genetic algorithm using sequence rule chain for multi-objective optimization in re-entrant micro-electronic production line[J]. Robotics and computer-integrated manufacturing, 2004, 20(3): 225-236.
[112] 吕文彦 and 党延忠. 基于 B-T 规则与遗传算法的可重入生产系统调度[J]. 系统仿真学报, 2005, 17(4): 993-996.
[113] Jiang, H., et al. The new method of dynamic scheduling in semiconductor fabrication line[C]. in International conference on control, automation, robotics and vision. 2004. 1874-1878.
[114] Koole, G. and A. Pot. Workload Minimization in Re-entrant Lines[J]. European Journal of operation research, 2006, 174: 216-233.
[115] Choi, J.Y. and S.A. Reveliotis. Relative value function approximation for the capacitated re-entrant line scheduling problem[J]. IEEE Transactions on automation science and engineering, 2005, 2(3): 285-299.
[116] 王利存 and 郑应平. 可重入生产系统的递阶增强型学习调度[J]. 信息与控制, 2001, 30(3): 199-203.
[117] Kumar, P.R. Efficient scheduling policies to reduce mean and variance of cycle-time insemiconductor manufactuing plants[J]. IEEE Transactions on Semiconductor Manufacturing, 1994, 7(3): 374-388.
[118] 王颖,朱顺痣,许威,缪克华,李茂青. 基于神经元动态规划的可重入生产系统调度的仿真框架[J]. 信息与控制, 2007, 36(2): 218-223.
[119] Bertsekas, D.P. and J.N. Tsitsiklis. Neuro-dynamic programming. 1996: Athena scientific.
[120] 殷保群. 排队系统性能分析与 Markov 控制过程. 中国科学技术大学出版社, 2003, 合肥.
[121] Lu, S.H., D. Ramaswamy, and P.R. Kumar. Efficient scheduling policies to reduce mean and variance of cycle-time in semiconductor manufacturing plants[J]. IEEE Transactions on Semiconductor Manufacturing, 1994, 7(3): 374-385.
[122] Puterman,M.L., Markov decision process discrete stochastic dynamic programming[M]. 2005, New Jersey: John Wiley&Sons.
[123] Bertsekas, D.P. and J.N. Tsitsiklis, Neuro-Dynamic Programming: An Overview[C]. Conference on Decision and Control. 1995.
[124] 何毓琦, 优化——光彩夺目的世界[M]. 1999: 西安交通大学出版社.
[125] Minsky, M.L., Theory of neural analog reinforcement system and its application to the brain model problem[M]. 1954, New Jersey: USA Princeton Univ.
[126] Sutton, R.S., Learning to Predict by the Methods of Temporal Difference[J]. Machine learning, 1988. 3:9-44.
[127] Cichosz, P., Truncating temporal differences: on the efficient implementation of TD for reinforcement learning[J]. Artificial Intelligence Research, 1996.12:287-318.
[128] Dayan, P., The convergence of TD(λ) for general λ[J]. Machine learning, 1992. 8: 341-362.
[129] Badtke, S.J. and R.G. Barto, Linear least squares algorithms for temporal difference Learning[J]. Machine learning, 1996.22:33-57.
[130] Yu, H. and D.P. Bertsekas, Convergence Results for Some Temporal Difference Methods Based on Least Squares[Z]. 2006, LIDS-2697.
[131] Bertsekas, D.P., Improved Temporal Difference Methods with Linear Function Approximation[Z]. 2003, LIDS-2573.
[132] Watkins, J.C., Learning from delayed rewards[D]. 1989, Cambridge.
[133] Watkins, J.C. and P. Dayan, Q-learning[J]. Machine learning, 1992.8:279-292.
[134] Tesauro, G.J., Issues on temporal difference learning[J]. Machine learning, 1992. 8:257-277.
[135] Zhang, W. A reinforcement learning approach to job shop scheduling[C]. 14th IJCAI.,1995
[136] Roy, B.V., D. Bertsimas, and J.N. Tsitsiklis. A neuro-dynamic programming approach to retailer inventory management[C]. 36th Conference on decision and control. 1997: 4052-4057.
[137] Marbach, P. and J.N. Tsitsiklis, A neuro-dynamic programming approach to admission control in ATM networks: the single link case[Z]. 1997, LIDS-2402.
[138] Crites, R.H. and A.G. Barto,. Improving elevator performance using reinforcement learning [J]. Advances in Neural Information Processing Systems, 1996,8:1017-1023.
[139] Singh, S. and D.Bertsekas, Reinforcement learning for dynamic channel allocation in cellular telephone systems[Z]. Advances in Neural Information Processing Systems.1997,9:974-980.
[140] Nie, J. and S. Haykin, A Q-learning-based dynamic channel assignment technique for mobile communication systems[J]. IEEE Transactions on Vehicular Technology, 1998,45(5):1676～1687.
[141] Nie, J. and S. Haykin, A dynamic channel assignment policy through Q-learning[R], in CRL Report NO.334. 1996, Communications research laboratory, McMaster University, Hamilton, Ontario.
[142] Bertsekas, D.P., et al., Mission defence and interceptor allocation by neuro-dynamic programming[J]. IEEE Transactions on systems, man and cybernetics, 2000. 30(1): 42-51.
[143] D.Bertsekas, 动态规划:确定性和随机性模型[M], ed. 李人厚,韩崇昭译. 1988, 西安: 西安交通大学出版社.
[144] 张有为, 动态规划[M]. 1991, 湖南: 湖南科学技术出版社.
[145] 金辉宇, 神经元动态规划在可重入生产系统调度中的应用[D]. 2001, 中国科学院沈阳自动化研究所.
[146] Choi, J.Y., Performance Modeling, Analysis and Control of capacitated re-entrant lines[D].2004, Georgia Institute of Technology.
[147] Kumar, P.R., Scheduling manufacturing systems for re-entrant lines[C], Stochastic modeling and analysis of manufacturing systems. 1994, 325-360.
[148] Lu, S.H., D. Ramaswamy, and P.R. Kumar, Efficient scheduling policies to reduce mean and variance of cycle-time in semiconductor manufacturing plants[J]. IEEE Transactions on Semiconductor Manufacturing, 1994. 7(3): 374-385.