Bottleneck Prediction Method Based on Improved Adaptive Network-based Fuzzy Inference System (ANFIS) in Semiconductor Manufacturing System*

Chinese Journal of Chemical Engineering ›› 2012, Vol. 20 ›› Issue (6): 1081-1088.

Bottleneck Prediction Method Based on Improved Adaptive Network-based Fuzzy Inference System (ANFIS) in Semiconductor Manufacturing System^*

曹政才^1,2, 邓积杰¹, 刘民³, 王永吉⁴

1. College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China;
2. Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing 210096, China;
3. Tsinghua National Laboratory for Information Science and Technology, Beijing 100084, China;
4. State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing 100190, China

收稿日期:2012-05-21 修回日期:2012-07-14 出版日期:2012-12-28 发布日期:2012-12-28
通讯作者: CAO Zhengcai,E-mail:giftczc@163.com
基金资助:
Supported by the National Key Basic Research and Development Program of China (2009CB320602);the National Natural Science Foundation of China (60834004;61025018);the Open Project Program of the State Key Lab of Industrial ControlTechnology (ICT1108);the Open Project Program of the State Key Lab of CAD & CG (A1120);the Foundation of Key Laboratory of System Control and Information Processing (SCIP2011005);Ministry of Education;China

Bottleneck Prediction Method Based on Improved Adaptive Network-based Fuzzy Inference System (ANFIS) in Semiconductor Manufacturing System^*

CAO Zhengcai^1,2, DENG Jijie¹, LIU Min³, WANG Yongji⁴

1. College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China;
2. Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing 210096, China;
3. Tsinghua National Laboratory for Information Science and Technology, Beijing 100084, China;
4. State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing 100190, China

Received:2012-05-21 Revised:2012-07-14 Online:2012-12-28 Published:2012-12-28
Supported by:
Supported by the National Key Basic Research and Development Program of China (2009CB320602);the National Natural Science Foundation of China (60834004;61025018);the Open Project Program of the State Key Lab of Industrial ControlTechnology (ICT1108);the Open Project Program of the State Key Lab of CAD & CG (A1120);the Foundation of Key Laboratory of System Control and Information Processing (SCIP2011005);Ministry of Education;China

摘要/Abstract

摘要： Semiconductor manufacturing (SM) system is one of the most complicated hybrid processes involved continuously variable dynamical systems and discrete event dynamical systems.The optimization and scheduling of semiconductor fabrication has long been a hot research direction in automation.Bottleneck is the key factor to a SM system,which seriously influences the throughput rate,cycle time,time-delivery rate,etc.Efficient prediction for the bottleneck of a SM system provides the best support for the consequent scheduling.Because categorical data (product types,releasing strategies) and numerical data (work in process,processing time,utilization rate,buffer length,etc.) have significant effect on bottleneck,an improved adaptive network-based fuzzy inference system (ANFIS) was adopted in this study to predict bottleneck since conventional neural network-based methods accommodate only numerical inputs.In this improved ANFIS,the contribution of categorical inputs to firing strength is reflected through a transformation matrix.In order to tackle high-dimensional inputs,reduce the number of fuzzy rules and obtain high prediction accuracy,a fuzzy c-means method combining binary tree linear division method was applied to identify the initial structure of fuzzy inference system.According to the experimental results,the main-bottleneck and sub-bottleneck of SM system can be predicted accurately with the proposed method.

关键词: semiconductor manufacturing system, bottleneck prediction, adaptive network-based fuzzy inference system

Abstract: Semiconductor manufacturing (SM) system is one of the most complicated hybrid processes involved continuously variable dynamical systems and discrete event dynamical systems.The optimization and scheduling of semiconductor fabrication has long been a hot research direction in automation.Bottleneck is the key factor to a SM system,which seriously influences the throughput rate,cycle time,time-delivery rate,etc.Efficient prediction for the bottleneck of a SM system provides the best support for the consequent scheduling.Because categorical data (product types,releasing strategies) and numerical data (work in process,processing time,utilization rate,buffer length,etc.) have significant effect on bottleneck,an improved adaptive network-based fuzzy inference system (ANFIS) was adopted in this study to predict bottleneck since conventional neural network-based methods accommodate only numerical inputs.In this improved ANFIS,the contribution of categorical inputs to firing strength is reflected through a transformation matrix.In order to tackle high-dimensional inputs,reduce the number of fuzzy rules and obtain high prediction accuracy,a fuzzy c-means method combining binary tree linear division method was applied to identify the initial structure of fuzzy inference system.According to the experimental results,the main-bottleneck and sub-bottleneck of SM system can be predicted accurately with the proposed method.

Key words: semiconductor manufacturing system, bottleneck prediction, adaptive network-based fuzzy inference system

曹政才, 邓积杰, 刘民, 王永吉. Bottleneck Prediction Method Based on Improved Adaptive Network-based Fuzzy Inference System (ANFIS) in Semiconductor Manufacturing System^*[J]. Chinese Journal of Chemical Engineering, 2012, 20(6): 1081-1088.

CAO Zhengcai, DENG Jijie, LIU Min, WANG Yongji. Bottleneck Prediction Method Based on Improved Adaptive Network-based Fuzzy Inference System (ANFIS) in Semiconductor Manufacturing System^*[J]. Chin.J.Chem.Eng., 2012, 20(6): 1081-1088.

参考文献

1 Chen,L.,Huang,Y.L.,"Integrated product and process control for sustainable semiconductor manufacturing",Chin.J.Chem.Eng.,19 (2),192-198 (2011).
2 Chen,J.H.,Fu,L.C.,Lin,M.H.,Huang,A.C.,"Petri-net and GA-based approach to modeling,scheduling,and performance evaluation for wafer fabrication",IEEE Transactions on Robotics and Automation,17 (5),619-636 (2001).
3 Cao,Z.C.,Peng,Y.Z.,Wang,Y.J.,"A drum-buffer-rope based scheduling method for semiconductor manufacturing system",In: 2011 IEEE Conference on Automation Science and Engineering,Wang,M.Y.,ed.,IEEE Publications,Italy,120-125 (2011).
4 Meidan,Y.,Lerner,B.,Rabinowitz,G.,Hassoun,M.,"Cycle-time key factor identification and prediction in semiconductor manufacturing using machine learning and data mining",IEEE Transactions on Semiconductor Manufacturing,24 (2),237-248 (2011).
5 Topaloglu,S.,Kilincli,G.,"A modified shifting bottleneck heuristic for the reentrant job shop scheduling problem with makespan mini-mization," The International Journal of Advanced Manufacturing Technology,44 (7-8),781-794 (2009).
6 Lin,L.,Qing,C.,Jun,N.,"Data driven bottleneck detection of manufacturing systems," International Journal of Production Research,47 (18),5019-5036 (2009).
7 Ye,T.F.,Han,W.M.,"Method of simulation on determining bottleneck resource",Journal of East China Shipbuilding Institute (Natural Science Edition),17 (4),80-84 (2005).(in Chinese)
8 Moss,H.K.,Yu,W.B.,"Toward the estimation of bottleneck shiftiness in a manufacturing operation",Production and Inventory Management Journal,40 (2),53-58 (1999).
9 Liu,M.Z.,Tang,J.,Ge,M.,Jiang,Z.Q.,Hu,J.,Ling,L.,"Dynamic prediction method of production logistics bottleneck based on bottleneck index",Chinese Journal of Mechanical Engineering,22 (5),710-716 (2009).
10 Jang,J.S.R.,"ANFIS: Adaptive-network-based fuzzy inference system",IEEE Transactions on Systems,Man,and Cybernetics,23 (3),665-685 (1993).
11 Liu,M.,Dong,M.Y.,Wu,C.,"A new ANFIS for parameter prediction with numeric and categorical inputs",IEEE Transactions on Automation Science and Engineering,7 (3),645-653 (2010).
12 Khazraee,S.M.,Jahanmiri,A.H.,"Composition estimation of reactive batch distillation by using adaptive neuro-fuzzy inference system",Chin.J.Chem.Eng.,18 (4),703-710 (2010).
13 Huang,H.P.,Chen,T.Y.,"A new approach to on-line rescheduling for a semiconductor foundry fab",In: Proceedings of International Conference on System,Man and Cybernetics,Wu,B.F.,ed.,IEEE Publications,Taiwan,4727-4732 (2006).
14 Wang,W.P.,Chen,Z.,"A neuro-fuzzy based forecasting approach for rush order control applications",Expert System with Applications,35 (1),223-234 (2008)
15 Zhang,M.,Yu,J.,"Fuzzy partitional clustering algorithms",Journal of Software,15 (6),858-868 (2004).(in Chinese)
16 Yue,Y.F.,Mao,J.Q.,"Fast adaptive modeling based on T-S model",Control and Decision,17(2),155-158 (2002).(in Chinese)
17 Wang,Z.T.,Wu,Q.D.,Qiao,F.,"A lot dispatching strategy integrating WIP management and wafer start control",IEEE Transactions on Automation Science and Engineering,4 (4),579-583 (2007).

Bottleneck Prediction Method Based on Improved Adaptive Network-based Fuzzy Inference System (ANFIS) in Semiconductor Manufacturing System^*

Bottleneck Prediction Method Based on Improved Adaptive Network-based Fuzzy Inference System (ANFIS) in Semiconductor Manufacturing System^*

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价