Abstract
With the rapid development of the TFT-LCD manufacturing, in order to maintain competitiveness, effectively control of the production process to enhance the yield has become the key issue for panel factories. To ensure the assignable root cause of the yeild loss, inline inspection system has applied to identify defects on the panel. Engineers rely on the information from the inline inspection system for trouble shooting, one of most effective way is to analyze the clustering pattern of defect map. Defect map can provide important rules for engineers to find the root cause by identifying patterns correctly. Nowadays, most companies still rely on engineers’ experiences of visual inspections and personal judgments in the map patterns. This manual approach is not only subjective, lack of justice and consistent standard, but also very time consuming and inefficient. This study proposes a data mining framework of line defects for identifying clustering pattern of the defect map and the root cause of the clustering pattern of defect map. First, critical defect map which possesses potential clustering pattern is testing for run test to classified into Random and Clustered. For the clustered map, applying change point analysis to determine the position of the defect cluster, and find the root cause of each clustering pattern by LASSO. To examine the validity of this approach, an empirical study was conducted in a TFT-LCD company in Taiwan. The results show that the framework can identify the clustering pattern of the defect map and the root cause effectively.