Constructing Control Process for Wafer Defects Using Data Mining Technique

Authors

Leeing Tong, Department of Industrial Engineering and Management, National Chiao Tung University, Hsinchu, TaiwanFollow
Hsingyin Lee, Department of Industrial Engineering and Management, National Chiao Tung University, Hsinchu, TaiwanFollow
Chifeng Huang, Department of Industrial Engineering and Management, National Chiao Tung University, Hsinchu, TaiwanFollow
Changke Lin, Department of Industrial Engineering and Management, National Chiao Tung University, Hsinchu, TaiwanFollow
Chienhui Yang, Department of Industrial Engineering and Management, National Chiao Tung University, Hsinchu, TaiwanFollow

Document Type

Article

Abstract

The wafer defects influence the yield of a wafer. The integrated circuits (IC) manufacturers usually use a Poisson distribution based c-chart to monitor the lot-to-lot wafer defects. As the wafer size increases, defects on wafer tend to cluster. When the c-chart is used, the clustered defects frequently cause erroneous results. The main objective of this study is to develop a hierarchical adaptive control process to monitor the clustered defects effectively and detect the wafer-to-wafer variation and lot-to-lot variation simultaneously using data mining technique.

Recommended Citation

Tong, Leeing; Lee, Hsingyin; Huang, Chifeng; Lin, Changke; and Yang, Chienhui, "Constructing Control Process for Wafer Defects Using Data Mining Technique" (2004). ICEB 2004 Proceedings (Beijing, China). 208.
https://aisel.aisnet.org/iceb2004/208