The Research of Quality Prediction Model for Touch Panel Manufacturing

• Main Authors: Ming-Shiun Lin, 林明勳
• Other Authors: S.Y. Hwang
• Format: Others
• Language: zh-TW
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/87438043114050566939

碩士 === 國立中山大學 === 資訊管理學系研究所 === 101 === Improving manufacturing yield is the major concern of IT manufacturing industry IIn panel manufacturing industry, large-size panels are no longer a priority due to the decline of gross profit. As a result, many panel manufacturers have moved their fifth or even sixth generation large panel manufacturing factories to China. How to manufacture small and medium sized touch panel for mobile devices with higher yield becomes the main concern of many panel manufacturers. Small and medium-size touch panel manufacturing process is more complicated and usually has lower yield than large-sized panel manufacturing. Panel manufacturers these days are struggling to find effective ways to improve their production yields. This thesis proposes to apply decision tree method to examine a large number of settings and measured data collected from production process to uncover the factors that mostly affect the quality of the touch panel during the manufacturing process. The results show that untrained accuracy of the data Precision/Recall can reach up to 85%, effectively identifying the key parameters factor. The results can be used in the front-end panel manufacturing to properly adjust the key parameters in order to achieve effective control of production quality and increase the number of units produced.