晶圓片製造過程包含數百道製程，每一道製程都是由一連串生產步驟所組成。其中我們可以簡單地將生產過程分為以下幾個大項，分別是氧化、光刻技術、蝕刻技術、離子植入、拋光平坦化和金屬濺鍍。這些步驟會在晶圓片不同的光罩以及不同的參數設定下，重複循環進行著。部分生產步驟後面會緊接著量測站點以即時監控每道製程下，晶圓片的生產品質。但是，隨著半導體界邁入奈米製程，產品規格也變得越細緻且需要特別的量測器具加以輔助。即便每一道製程下，晶圓片都嚴格控管在管制界線內，但仍有部分晶圓片上的晶粒最後會呈現缺陷。因此，本篇論文旨在提出一套分析流程，利用統計製程管制想法以及迴歸樹模型，想要觀察哪些Inline量測值趨勢變化會導致高缺陷率的產生。這個分析流程結合兩種資料類型，分別是Inline量測資料和良率資料，合併兩種資料資訊可以更貼切地觀察晶圓片在每道製程下品質衰退的過程。分析結果中所有資料都經過適當的轉換以保護資料來源。

Wafer fabrication contains hundreds of a series of process steps, including oxidation, photolithography, etching, ion implantation, planarization, metallization and so on. These steps are repeated over layers in a specific sequence with different masks and parameter setting. After a round of process steps, the inspection system follows and monitors whether the process is under control. However, as the semiconductor technology has stepped into the nano-fabrication process, the tolerance of specification has become even tighter. Although the in-line measurements of the shot, the exposed unit in photolithography process, on each layer is within the control limit, it is possible that some dies within the shot end up being defective. This study aims to propose a framework for analysing abnormal in-line measurements paths between processes within layer by introducing the idea of statistical process control and regression tree. The proposed framework, integrating two kinds of datasets, in-line measurements data and circuit probe test data, provides a better understanding of how the wafer degrades. The yield rates were modified to maintain confidentiality of the real data.

References
涂志豪(2017). 7 奈米明年量產5 奈米後年試產. http://www.chinatimes.com/newspapers/20170526000054-260202. Online; accessed 1 July 2017.
Breiman, L., Friedman, J., Stone, C. J., and Olshen, R. A. (1984). Classification and regression trees. CRC press.
Chen, F.-L. and Liu, S.-F. (2000). A neural-network approach to recognize defect spatial pattern in semiconductor fabrication. IEEE transactions on semiconductor manufacturing,13(3):366–373.
Chien, C.-F., Hsu, S.-C., and Chen, Y.-J. (2013). A system for online detection and classification of wafer bin map defect patterns for manufacturing intelligence. International Journal of Production Research, 51(8):2324–2338.
Chien, C.-F., Liu, C.-W., and Chuang, S.-C. (2015). Analysing semiconductor manufacturing big data for root cause detection of excursion for yield enhancement. International Journal of Production Research, pages 1–13.
Friedman, J., Hastie, T., and Tibshirani, R. (2001). The elements of statistical learning, volume 1. Springer series in statistics New York.
ITRS (2015). International Technology Roadmap for Semiconductors 2.0 2015 Edition. http://www.semiconductors.org/main/2015_international_technology_roadmap_for_semiconductors_itrs. Online; accessed 1 July 2017.
Jin, R. and Shi, J. (2012). Reconfigured piecewise linear regression tree for multistage manufacturing process control. IIE Transactions, 44(4):249–261.
Krueger, D. C., Montgomery, D. C., and Mastrangelo, C. M. (2011). Application of generalized linear models to predict semiconductor yield using defect metrology data. IEEE Transactions on Semiconductor Manufacturing, 24(1):44–58.
Liu, C.-W. and Chien, C.-F. (2013). An intelligent system for wafer bin map defect diagnosis: An empirical study for semiconductor manufacturing. Engineering Applications of Artificial Intelligence, 26(5):1479–1486.
Liu, S., Chen, F., and Lu, W. (2002). Wafer bin map recognition using a neural network approach. International Journal of production research, 40(10):2207–2223.
Lu, C.-J., Shao, Y. E., and Li, P.-H. (2011). Mixture control chart patterns recognition using independent component analysis and support vector machine. Neurocomputing, 74(11):1908–1914.
May, G. S. and Spanos, C. J. (2006). Fundamentals of semiconductor manufacturing and process control. John Wiley & Sons.
Pham, D. and Wani, M. (1997). Feature-based control chart pattern recognition. International Journal of production research, 35(7):1875–1890.
Qin, S. J., Cherry, G., Good, R., Wang, J., and Harrison, C. A. (2006). Semiconductor manufacturing process control and monitoring: A fab-wide framework. Journal of Process Control, 16(3):179–191.
Shi, J. and Zhou, S. (2009). Quality control and improvement for multistage systems: A survey. IIE Transactions, 41(9):744–753.
Su, A.-J., Yu, C.-C., and Ogunnaike, B. A. (2008). On the interaction between measurement strategy and control performance in semiconductor manufacturing. Journal of Process Control, 18(3):266–276.
Wang, C.-H., Kuo, W., and Bensmail, H. (2006). Detection and classification of defect patterns on semiconductor wafers. IIE Transactions, 38(12):1059–1068.
Wu, L. and Zhang, J. (2010). Fuzzy neural network based yield prediction model for semiconductor manufacturing system. International Journal of Production Research, 48(11):3225–3243.
Zhou, C., Ross, R., Vickery, C., Metteer, B., Gross, S., and Verret, D. (2002). Yield prediction using critical area analysis with inline defect data. In Advanced Semiconductor Manufacturing 2002 IEEE/SEMI Conference and Workshop, pages 82–86. IEEE.