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

被引：29

作者：

Li, Der-Chiang ^{[1
]}

Chen, Wen-Chih ^{[1
]}

Liu, Chiao-Wen ^{[1
]}

Lin, Yao-San ^{[1
]}

机构：

[1] Natl Cheng Kung Univ, Dept Ind & Informat Management, Tainan 70101, Taiwan

来源：

JOURNAL OF INTELLIGENT MANUFACTURING | 2012年 / 23卷 / 03期

关键词：

Dependent factor; SVR; Multi-regression; TFT-LCD; Color filter; Quality control; KNOWLEDGE;

D O I：

10.1007/s10845-010-0440-1

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：835 / 844

页数：10

共 19 条

[1] A meta-learning approach to automatic kernel selection for support vector machines [J].