The application of clustering analysis for the critical areas on TFT-LCD panel

摘要

For thin film transistor-liquid crystal displays (TFT-LCD) factories in Taiwan, yield performance had become as an important competitiveness determinant during the competitive environment. As we known, the market for LCDs has grown at over 20% on average per annum and the downward pricing trend had also promoted LCD applications. However, only few studies were proposed to address the related issues for process analysis in TFT-LCD industry from the viewpoint of systems. Particularly, the defect status (i.e. abnormal position) on TFT-LCD panel may represent the clustering effect when there are many defect counts on it. Hence, performing the clustering analysis for those abnormal positions will be an important issue to be addressed in TFT-LCD process. In this study, we will propose an approach incorporating fuzzy adaptive resonance theory (Fuzzy ART) and stepwise regression techniques to achieve such process analysis. Besides, an illustrative case owing to TFT-LCD manufacturer at Tainan Science Park in Taiwan will be applied to verifying the rationality and feasibility of our proposed procedure.