Evolving CBR and data segmentation by SOM for flow time prediction in semiconductor manufacturing factory

Flow time of semiconductor manufacturing factory is highly related to the shop floor status; however, the processes are highly complicated and involve more than 100 production steps. Therefore, a simulation model with the production process of a real wafer fab located in Hsin-Chu Science-based Park of Taiwan is built for further studying of the relationship between the flow time and the various input variables. In this research, a hybrid approach by combining Self-Organizing Map (SOM) and Case-Based Reasoning (CBR) for flow time prediction in semiconductor manufacturing factory is developed. And Genetic Algorithm (GA) is applied to fine-tune the weights of features in the CBR model. The flow time and related shop floor status are collected and fed into the SOM for clustering. Then, a corresponding SGA-CBR method is selected and applied for flow time prediction. Finally, using the simulated data, the effectiveness of the proposed method (SGA-CBR) is shown by comparing with other approaches.

[1]  Dong-Ping Song,et al.  Product due date assignment for complex assemblies , 2002 .

[2]  Vassilis S. Kodogiannis,et al.  Forecasting Financial Time Series using Neural Network and Fuzzy System-based Techniques , 2002, Neural Computing & Applications.

[3]  Pei-Chann Chang,et al.  A Case-Based Reasoning Approach for Due-Date Assignment in a Wafer Fabrication Factory , 2001, ICCBR.

[4]  C. Siriopoulos,et al.  Combinatorial time series forecasting based on clustering algorithms and neural networks , 2004, Neural Computing & Applications.

[5]  G. Ragatz,et al.  A simulation analysis of due date assignment rules , 1984 .

[6]  Selwyn Piramuthu,et al.  Financial credit-risk evaluation with neural and neurofuzzy systems , 1999, Eur. J. Oper. Res..

[7]  D. Sculli.  The Completion Time of PERT Networks , 1983 .

[8]  Candace Aral Yano,et al.  Stochastic Leadtimes in Two-Level Assembly Systems , 1987 .

[9]  Toly Chen,et al.  Predicting Wafer-Lot Output Time With a Hybrid FCM–FBPN Approach , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[10]  L. P. Rees,et al.  Cost‐based due‐date assignment with the use of classical and neural‐network approaches , 1997 .

[11]  William L. Maxwell,et al.  Theory of scheduling , 1967 .

[12]  Toly Chen,et al.  A Hybrid SOM-BPN Approach to Lot Output Time Prediction in a Wafer Fab , 2006, Neural Processing Letters.

[13]  Cheng-Jian Lin,et al.  A self-adaptive neural fuzzy network with group-based symbiotic evolution and its prediction applications , 2006, Fuzzy Sets Syst..

[14]  Pei-Chann Chang,et al.  A fuzzy neural network for the flow time estimation in a semiconductor manufacturing factory , 2008 .

[15]  Zvi Drezner,et al.  A Multivariate Approach to Estimating the Completion Time for PERT Networks , 1986 .

[16]  Phillip Burrell,et al.  Case-Based Reasoning System and Artificial Neural Networks: A Review , 2001, Neural Computing & Applications.

[17]  Toly Chen,et al.  An intelligent hybrid system for wafer lot output time prediction , 2007, Adv. Eng. Informatics.

[18]  Ian D. Watson,et al.  A Distributed Case-Based Reasoning Application for Engineering Sales Support , 1999, IJCAI.

[19]  Salah E. Elmaghraby,et al.  Optimal start times under stochastic activity durations , 2000 .

[20]  Pei-Chann Chang,et al.  A case-based expert support system for due-date assignment in a wafer fabrication factory , 2003, J. Intell. Manuf..

[21]  Jih-Chang Hsieh,et al.  A neural networks approach for due-date assignment in a wafer fabrication factory , 2003 .

[22]  Pierpaolo Pontrandolfo,et al.  Project duration in stochastic networks by the PERT-path technique , 2000 .

[23]  Lyle H. Ungar,et al.  Neural network forecasting of short, noisy time series , 1992 .

[24]  James K. Weeks.  A Simulation Study of Predictable Due-Dates , 1979 .

[25]  Lijuan Cao,et al.  Support vector machines experts for time series forecasting , 2003, Neurocomputing.

[26]  James H. Bookbinder,et al.  Setting Job-Shop Due-Dates with Service-Level Constraints , 1985 .

[27]  Otávio Augusto S. Carpinteiro,et al.  A hierarchical neural model with time windows in long-term electrical load forecasting , 2007, Neural Computing and Applications.

[28]  T.C.E. Cheng,et al.  Survey of scheduling research involving due date determination decisions , 1989 .

[29]  Ruy Luiz Milidiú,et al.  Time-series forecasting through wavelets transformation and a mixture of expert models , 1999, Neurocomputing.

[30]  Pei-Chann Chang,et al.  Combining SOM and fuzzy rule base for flow time prediction in semiconductor manufacturing factory , 2006, Appl. Soft Comput..

[31]  Pei-Chann Chang,et al.  Evolving fuzzy rules for due-date assignment problem in semiconductor manufacturing factory , 2005, J. Intell. Manuf..

[32]  Lazaros S. Iliadis,et al.  Time-series modeling of fishery landings using ARIMA models and Fuzzy Expected Intervals software , 2006, Environ. Model. Softw..

[33]  Cheng-Chin Chiang,et al.  A hybrid approach of neural networks and grey modeling for adaptive electricity load forecasting , 2006, Neural Computing & Applications.

[34]  E. M. Anagnostakis,et al.  Short-term load forecasting based on artificial neural networks parallel implementation , 2002 .

[35]  Toly Chen,et al.  A Fuzzy-Neural Approach with BPN Post-classification for Job Completion Time Prediction in a Semiconductor Fabrication Plant , 2007, Analysis and Design of Intelligent Systems using Soft Computing Techniques.

[36]  P. Backus,et al.  Factory cycle-time prediction with a data-mining approach , 2006, IEEE Transactions on Semiconductor Manufacturing.

[37]  Pei-Chann Chang,et al.  A hybrid system combining self-organizing maps with case-based reasoning in wholesaler's new-release book forecasting , 2005, Expert Syst. Appl..