面板產業為資本密集且高度競爭的高科技產業，為了維持競爭優勢，開始使用四道光罩技術於製程當中，透過使用半色調網點光罩，能使製程道數減少，然而此類光罩容易導致光阻厚度不均的情況，因此需透過檢測以確保產品品質。廠商在考慮時間成本與資本設備成本的情況下，會使用抽檢來監督產品品質，但抽檢並無法保證全面品質管理，因此本研究建立光阻膜厚之虛擬量測模式，透過蒐集過去機台參數資料，使用偏最小平方法（partial least squares, PLS），建構光阻膜厚預測模型。此虛擬量測模式建立後，不僅能使機台的量測頻率減少，更能協助監測整個生產設備，即時反應異常製程，減少產品作業週期，達到高效能高產能的目標。並與台灣某知名光電面板公司合作，進行實證研究，透過平均絕對百分比誤差（mean absolute percent error, MAPE）檢驗方法效度。驗證資料組之平均絕對百分比誤差為3.96%，代表此模型的預測能力良好。

In a highly competitive and capital-intensive industry, such as panel industry. To keep its competitive advantage, panel industry try to use the halftone mask into the process. Using halftone mask reduce the process flow into four. However, halftone mask easily lead to resist non-uniformity, these make panel industry need to control the resist uniformity to make sure that product quality is fine. Considering the cost of time and equipmetn, industry always use sampling to monitor the product quality, but sampling does not guarantee total quality management. In this study, we collect history data, using partial least squares to construct a virtual metrology framework to predict the halftone thickness. After the prediction model is built, not only reduce the frequency of measuring but help panel industry to inspect the whole production equipment, react deviant problem and reduce product cycle time then achieve high capacity goals. By cooperating with a well-known Taiwanese panel company to test the method validity and the MAPE of the validation data set was 3.96%, means a good representative of the prediction model.

表目錄 iii
圖目錄 iv
第一章 緒論 1
1.1 研究背景、動機與重要性 1
1.2 研究目的 2
1.3 論文結構 2
第二章 文獻回顧（理論基礎） 4
2.1 TFT-LCD製程簡介 4
2.2 虛擬量測（Virtual Metrology） 6
2.3 偏最小平方法（Partial Least Squares, PLS） 7
第三章 研究架構 10
3.1 問題定義 12
3.2 資料準備 12
3.2.1 資料蒐集與檢視 12
3.2.2 資料清理 13
3.2.3 資料轉換 14
3.2.4 資料分割 14
3.3 模型建構 14
3.3.1 交互驗證找出最佳模型參數 14
3.3.2 建立膜厚預測模式 15
3.3.3 效度檢驗 16
3.4 結果評估與解釋 17
3.4.1 模型應用 17
第四章 實證研究 18
4.1 問題定義 18
4.2 資料準備 19
4.2.1 資料蒐集與檢視 19
4.2.2 資料清理 21
4.2.3 資料轉換 22
4.2.4 資料分割 22
4.3 模型建構 22
4.3.1 交互驗證找出最佳模型參數 22
4.3.2 建立膜厚預測模式 23
4.3.3 效度檢驗 25
4.4 結果評估與解釋 25
4.4.1模型應用 25
第五章 結論與後續研究方向 26
5.1 研究結論 26
5.2 後續研究方向 27
參考文獻 28

田民波（2008），平面顯示器之技術發展，五南圖書，台北。
簡禎富、許嘉裕（2014），資料挖礦與大數據分析，前程文化，台北。
Besnard, J., Gleispach, D., Gris, H., Ferreira, A., Roussy, A., Kernaflen, C., and Hayderer, G. (2012), "Virtual metrology modeling for cvd film thickness," International Journal of Control Science and Engineering, Vol. 2, No. 3, pp. 26-33.
Chang, Y.-J. (2010), "Wavelet-based virtual metrology technique," Proceedings of IEEE International Conference on Mechatronics and Automation, pp. 367-371.
Chang, Y.-J., Kang, Y., Hsu, C.-L., Chang, C.-T., and Chan, T. Y. (2006), "Virtual metrology technique for semiconductor manufacturing," Proceedings of IEEE International Joint Conference on Neural Network, pp. 5289-5293.
Chen, P., Wu, S., Lin, J., Ko, F., Lo, H., Wang, J., Yu, C., and Liang, M. (2005), "Virtual metrology: a solution for wafer to wafer advanced process control," Proceedings of IEEE International Symposium on Semiconductor Manufacturing, pp. 155-157.
Devarakonda, N., Subhani, S., and Basha, S. A. H. (2014), "Outliers detection in regression analysis using partial least square approach," Advances in Intelligent Systems and Computing, Vol. 249, pp. 125-135.
Ding, B. and Gentleman, R. (2012), "Classification using generalized partial least squares," Journal of Computational and Graphical Statistics, Vol. 14, No. 2, pp. 280-298.
Eriksson, L. (2006), Multi- and Megavariate Data Analysis, Part 2, Advanced Applications and Method Extensions. Umetrics AB.
Eriksson, L., Byrne, T., Johansson, E., Trygg, J., and Vikström, C. (2013), Multi-and megavariate data analysis basic principles and applications. Umetrics Academy.
Garthwaite, P. H. (1994), "An interpretation of partial least squares," Journal of the American Statistical Association, Vol. 89, No. 425, pp. 122-127.
Geladi, P. and Kowalski, B. R. (1986), "Partial least-squares regression: a tutorial," Analytica chimica acta, Vol. 185, pp. 1-17.
Hung, M.-H., Lin, T.-H., Cheng, F.-T., and Lin, R.-C. (2007), "A novel virtual metrology scheme for predicting CVD thickness in semiconductor manufacturing," IEEE/ASME Transactions on Mechatronics, Vol. 12, No. 3, pp. 308-316.
Jonathan, C. Y.-C. and Cheng, F.-T. (2005), "Application development of virtual metrology in semiconductor industry," 31st Annual Conference of IEEE Industrial Electronics Society, pp. 124-129.
Khan, A. A., Moyne, J. R., and Tilbury, D. M. (2008), "Virtual metrology and feedback control for semiconductor manufacturing processes using recursive partial least squares," Journal of Process Control, Vol. 18, No. 10, pp. 961-974.
Lin, L.-R., Chiu, Y.-C., Mo, W.-C., Kao, C.-A., Liu, T.-M., Zeng, D.-L., and Cheng, F.-t. (2011), "Run-to-run control utilizing the avm system in the solar industry," Proceedings of International Symposium on Semiconductor Manufacturing and e-Manufacturing and Design Collaboration Symposium, pp. 1-33.
Lin, T.-H., Hung, M.-H., Lin, R.-C., and Cheng, F.-T. (2006), "A virtual metrology scheme for predicting CVD thickness in semiconductor manufacturing," Proceedings of IEEE International Conference on Robotics and Automation, pp. 1054-1059.
Lindberg, W., Persson, J.-Å., and Wold, S. (1983), "Partial least-squares method for spectrofluorimetric analysis of mixtures of humic acid and lignin sulfonate," Analytical Chemistry, Vol. 55, No. 4, pp. 643-648.
Livingstone, D. J. (2009), A practical guide to scientific data analysis. John Wiley & Sons.
Lvova, L., Galloni, P., Floris, B., Lundström, I., Paolesse, R., and Natale, C. D. (2013), "A ferrocene-porphyrin ligand for multi-transduction chemical sensor development," Sensors, Vol. 13, No. 5, pp. 5841-5856.
Mehmood, T. (2016), "Hotelling T 2 based variable selection in partial least squares regression," Chemometrics and Intelligent Laboratory Systems, Vol. 154, pp. 23-28.
Nomikos, P. and MacGregor, J. F. (1995), "Multi-way partial least squares in monitoring batch processes," Chemometrics and intelligent laboratory systems, Vol. 30, No. 1, pp. 97-108.
Oh, C.-H., Choi, H.-C., Hong, C.-H., and LCD, L. P. (2003), "Large TFT-LCD Manufacturing Technology," Electrochemical Society Proceedings, Vol. 2002, p. 1.
Ohsowski, B. M., Dunfield, K. E., Klironomos, J. N., and Hart, M. M. (2016), "Improving Plant Biomass Estimation in the Field Using Partial Least Squares Regression and Ridge Regression," Botany.
Olson, K. and Moyne, J. (2010), "Adaptive Virtual Metrology applied to a CVD process," Proceedings of IEEE/SEMI Advanced Semiconductor Manufacturing Conference (ASMC), pp. 353 - 358.
Pampuri, S., Schirru, A., Fazio, G., and De Nicolao, G. (2011), "Multilevel lasso applied to virtual metrology in semiconductor manufacturing," Proceedings of IEEE Conference on Automation Science and Engineering, pp. 244-249.
Pan, T.-H., Sheng, B.-Q., Wong, D. S.-H., and Jang, S.-S. (2011), "A virtual metrology model based on recursive canonical variate analysis with applications to sputtering process," Journal of Process Control, Vol. 21, No. 6, pp. 830-839.
Park, B. C., Park, E. S., Choi, B. K., Kim, B. H., and Lee, J. H. (2008), "Simulation based planning and scheduling system for TFT-LCD fab," Proceedings of the 40th conference on winter simulation, pp. 2271-2276.
Rosipal, R. and Krämer, N. (2006), "Overview and recent advances in partial least squares," Subspace, latent structure and feature selection, Springer, pp. 34-51.
Sheng, B.-Q. and Pan, T.-H. (2011), "Virtual metrology algorithm for TFT-LCD manufacutring process," Proceedings of Fuzzy Systems and Knowledge Discovery International Conference, pp. 34-51.
Sjöström, M., Wold, S., Lindberg, W., Persson, J.-Å., and Martens, H. (1983), "A multivariate calibration problem in analytical chemistry solved by partial least-squares models in latent variables," Analytica Chimica Acta, Vol. 150, pp. 61-70.
Song, K., Jang, P. Y., Cho, H., and Jun, C.-H. (2002), "Partial least square-based model predictive control for large-scale manufacturing processes," IIE Transactions, Vol. 34, No. 10, pp. 881-890.
Su, C.-T., Hsiao, Y.-H., and Liu, Y.-L. (2012), "Enhancing the fracture resistance of medium/small-sized TFT-LCDs using the Six Sigma methodology," IEEE Transactions on Components, Packaging and Manufacturing Technology, Vol. 2, No. 1, pp. 149-164.
Susto, G. A. (2013), "Statistical Methods for Semiconductor Manufacturing".
Tobias, R. D. (1995), "An introduction to partial least squares regression," Proceedings of the twentieth annual SAS users group international conference, pp. 1250-1257.
Tseng, F. M., Chiu, Y. J., and Chen, J. S. (2009), "Measuring business performance in the high-tech manufacturing industry: A case study of Taiwan's large-sized TFT-LCD panel companies," Omega, Vol. 37, No. 3, pp. 686-697.
Waits, C. M., Ghodssi, R., Ervin, M. H., and Dubey, M. (2001), "MEMS-based gray-scale lithography," Proceedings of IEEE International Semiconductor Device Research Symposium, pp. 182-185.
Westad, F. and Marten, H. (2000), "Variable selection in near infrared spectroscopy based on significance testing in partial least squares regression," Journal of Near Infrared Spectroscopy, Vol. 8, No. 2, pp. 117-124.
Wold, H. (1975), "Soft modeling by latent variables: the nonlinear iterative partial least squares approach," Perspectives in probability and statistics, pp. 520-540.
Wu, W.-M., Cheng, F.-T., Lin, T.-H., Zeng, D.-L., and Chen, J.-F. (2011), "Selection schemes of dual virtual-metrology outputs for enhancing prediction accuracy," IEEE Transactions on Automation Science and Engineering, Vol. 8, No. 2, pp. 311-318.
Zeng, D. and Spanos, C. J. (2009), "Virtual metrology modeling for plasma etch operations," IEEE Transactions on Semiconductor Manufacturing, Vol. 22, No. 4, pp. 419-431.