A non-linear quality improvement model using SVR for manufacturing TFT-LCDs

Thin Film Transistor—Liquid Crystal Displays (TFT-LCDs) are widely used in TVs, monitors, and PDAs. The key process of producing a TFT-LCD is using alignment to combine a Thin Film Transistor (TFT) panel with a Color Filter (CF) panel, which is called “celling”. The defined cell vernier, which indicates the alignment error, is an important quality index in the manufacturing process. In the CF manufacturing process, the cell vernier is difficult to control because it depends on six TPEs (Total Pitch Errors), with each TPE highly dependent on the others. This paper aims to improve the cell vernier forecasting model with the six TPE attributes to enhance the production yield in the CF manufacturing process. Using the six dependent variables, this study found that the SVR (Support Vector Machine for Regression) model is the fittest for generating quality results that meet the designed specifications.

[1]  Kate Smith-Miles,et al.  A meta-learning approach to automatic kernel selection for support vector machines , 2006, Neurocomputing.

[2]  Claudio Moraga,et al.  A diffusion-neural-network for learning from small samples , 2004, Int. J. Approx. Reason..

[3]  R. R. Hocking.  The analysis and selection of variables in linear regression , 1976 .

[4]  Ching-Hsue Cheng,et al.  Evaluating the risk of failure using the fuzzy OWA and DEMATEL method , 2011, J. Intell. Manuf..

[5]  Chih-Kai Chang,et al.  Optimal Scheduling in Color Filter Manufacturing , 2005 .

[6]  Vipin Kumar,et al.  Introduction to Data Mining , 2022, Data Mining and Machine Learning Applications.

[7]  Long-Sheng Chen,et al.  Using Functional Virtual Population as assistance to learn scheduling knowledge in dynamic manufacturing environments , 2003 .

[8]  Pei-Chann Chang,et al.  An evolutionary regulation algorithm for the twin laser measuring system , 2006, J. Intell. Manuf..

[9]  Fengming M. Chang,et al.  Using data continualization and expansion to improve small data set learning accuracy for early flexible manufacturing system (FMS) scheduling , 2006 .

[10]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[11]  Friedhelm Eicker,et al.  Linearly independent set families , 2004 .

[12]  Tomaso Poggio,et al.  Incorporating prior information in machine learning by creating virtual examples , 1998, Proc. IEEE.

[13]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[14]  A. V.DavidSánchez,et al.  Advanced support vector machines and kernel methods , 2003, Neurocomputing.

[15]  Vipin Kumar,et al.  Introduction to Data Mining, (First Edition) , 2005 .

[16]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[17]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[18]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[19]  Si Wu,et al.  Improving support vector machine classifiers by modifying kernel functions , 1999, Neural Networks.

[20]  Ian Witten,et al.  Data Mining , 2000 .

[21]  Der-Chiang Li,et al.  Using virtual sample generation to build up management knowledge in the early manufacturing stages , 2006, Eur. J. Oper. Res..