Title: Yield management in TFT-LCD manufacturing by using regression and neural network techniques

Authors: Kun-Lin Hsieh

Addresses: Department of Information Management, National Taitung University, 684, Sec.1, Chung-Hua Rd., R.O.C. Taitung County, 950 Taiwan

Abstract: Enhancing yield became an important competitive capability for thin film transistor-liquid crystal displays (TFT-LCD) manufacturers. Until now, few studies were proposed to address the related issues about the yield model via process analysis in TFT-LCD industry. Therefore, the useful information (e.g., the domain knowledge or the parameter effect) or the improvement chances which are hidden in process analysis will be frequently omitted. Hence, how to apply feasible technique into achieving the yield optimisation model by using the manufacturing processes will become a meaningful issue to be addressed in TFT-LCD industry. In this study, we proposed a feasible procedure, which incorporating the conventionally statistical technique and the artificial intelligence (AI), to achieve the construction of the yield optimisation model. Besides, a real illustrative case owing to TFT-LCD manufacturer at Tainan Science Park in Taiwan will be also applied to verify the rationality and feasibility of our proposed procedure.

Keywords: process analysis; thin film transistors; liquid crystal displays; TFT-LCD; backpropagation neural networks; BPNN; stepwise regression; yield models; Taiwan.

DOI: 10.1504/IJMTM.2010.032903

International Journal of Manufacturing Technology and Management, 2010 Vol.20 No.1/2/3/4, pp.300 - 315

Published online: 05 May 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article