A demonstration of machine learning for explicit functions for cycle time prediction using MES data

Cycle time prediction represents a challenging problem in complex manufacturing scenarios. This paper demonstrates an approach that uses genetic programming (GP) and effective process time (EPT) to predict cycle time using a discrete event simulation model of a production line, an approach that could be used in complex manufacturing systems, such as a semiconductor fab. These predictive models could be used to support control and planning of manufacturing systems. GP results in a more explicit function for cycle time prediction. The results of the proposed approach show a difference between 1–6% on the demonstrated production line.

[1]  Shengwei Ding,et al.  Queueing Theory for Semiconductor Manufacturing Systems: A Survey and Open Problems , 2007, IEEE Transactions on Automation Science and Engineering.

[2]  A. A. A. Kock,et al.  Effective process times for multi-server flowlines with finite buffers , 2008 .

[3]  Tom Bylander,et al.  Financial time series prediction and evaluation by genetic programming with trigonometric functions and high-order statistics , 2006 .

[4]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[5]  Mark J. Willis,et al.  Steady-state modelling of chemical process systems using genetic programming , 1997 .

[6]  Can Birkan,et al.  Evolutionary modelling of industrial systems with genetic programming , 2010 .

[7]  Pei-Chann Chang,et al.  Evolving CBR and data segmentation by SOM for flow time prediction in semiconductor manufacturing factory , 2009, J. Intell. Manuf..

[8]  Gad Rabinowitz,et al.  Cycle-Time Key Factor Identification and Prediction in Semiconductor Manufacturing Using Machine Learning and Data Mining , 2011, IEEE Transactions on Semiconductor Manufacturing.

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

[10]  J. Banks,et al.  Handbook of Simulation , 1998 .

[11]  Conor Ryan,et al.  A Simple Powerful Constraint for Genetic Programming , 2008, EuroGP.

[12]  Manoj Kumar Tiwari,et al.  Data mining in manufacturing: a review based on the kind of knowledge , 2009, J. Intell. Manuf..

[13]  Cathal Heavey,et al.  Generating operating curves in complex systems using machine learning , 2014, Proceedings of the Winter Simulation Conference 2014.

[14]  Cathal Heavey,et al.  Comparison of experimental designs for simulation-based symbolic regression of manufacturing systems , 2011, Comput. Ind. Eng..

[15]  Toly Chen,et al.  A hybrid neural network and selective allowance approach for internal due date assignment in a wafer fabrication plant , 2008 .

[16]  S. Hsu,et al.  Due-date assignment in wafer fabrication using artificial neural networks , 2004 .

[17]  Tsung-Che Chiang,et al.  Enhancing rule-based scheduling in wafer fabrication facilities by evolutionary algorithms: Review and opportunity , 2013, Comput. Ind. Eng..

[18]  John A. Buzacott,et al.  Stochastic models of manufacturing systems , 1993 .

[19]  Jacobus E. Rooda,et al.  Characterization of operational time variability using effective process times , 2003 .

[20]  Kit Yan Chan,et al.  Modeling manufacturing processes using a genetic programming-based fuzzy regression with detection of outliers , 2010, Inf. Sci..

[21]  Jerry Banks,et al.  Handbook of simulation - principles, methodology, advances, applications, and practice , 1998, A Wiley-Interscience publication.

[22]  C P L Veeger,et al.  Predicting Cycle Time Distributions for Integrated Processing Workstations: An Aggregate Modeling Approach , 2011, IEEE Transactions on Semiconductor Manufacturing.

[23]  Jeroen Eggermont,et al.  Data Mining using Genetic Programming : Classification and Symbolic Regression , 2005 .

[24]  László Monostori,et al.  AI and machine learning techniques for managing complexity, changes and uncertainties in manufacturing , 2003 .

[25]  John W. Fowler,et al.  Semiconductor Manufacturing Scheduling and Dispatching , 2006 .

[26]  Toly Chen.  A fuzzy back propagation network for output time prediction in a wafer fab , 2003, Appl. Soft Comput..

[27]  Theodore B. Trafalis,et al.  Real-time prediction of order flowtimes using support vector regression , 2008, Comput. Oper. Res..

[28]  Adil Baykasoglu,et al.  Gene expression programming based due date assignment in a simulated job shop , 2009, Expert Syst. Appl..

[29]  Shu-Hsien Liao,et al.  Data mining techniques and applications - A decade review from 2000 to 2011 , 2012, Expert Syst. Appl..

[30]  Min Xie,et al.  A systematic comparison of metamodeling techniques for simulation optimization in Decision Support Systems , 2010, Appl. Soft Comput..

[31]  Madhuchhanda Dasgupta,et al.  Least Absolute Deviation Estimation of Linear Econometric Models: A Literature Review , 2004 .

[32]  C P L Veeger,et al.  Generating Cycle Time-Throughput Curves Using Effective Process Time Based Aggregate Modeling , 2010, IEEE Transactions on Semiconductor Manufacturing.

[33]  Toly Chen,et al.  A fuzzy back propagation network ensemble with example classification for lot output time prediction in a wafer fab , 2009, Appl. Soft Comput..