在2011年德國政府提出工業4.0高科技計畫後，世界各國為了保持其優勢皆開始以智慧工廠為目標輔導企業轉型；其中虛擬量測的技術在半導體領域中扮演著重要的角色，虛擬量測可幫助提升產品良率、降低量測成本、提高產出率並且將產品量測從抽樣測量提升為全面測量；而虛擬量測在業界已有一定程度的發展，各公司皆已發展出各自的架構，但現行使用的模型為人工設定的數學模型居多，人工設定需花費大量時間，在相關參數的選擇上亦需倚賴製程人員的專業知識選擇，相對而言容易造成人為誤差，並且無法針對複雜的量測參數進行預測。
故本研究提出以現有架構為基準，並以深度學習模型取代現有人工設定模型的改良做法，以減少人力花費，並降低模型對製程人員專業知識的倚賴程度，且能支援複雜的量測參數預測，本研究以Pure NN結合Rule Based Improved NN加上Weight NN的深度學習模型架構進行訓練，深度學習數學模型平均誤差值為0.044相較於人工設定數學模型的平均誤差值0.05，有更準確的預測結果，證明以深度學習模型取代目前人工設定數學模型的可行性。

After the German government proposed the Industry 4.0 high-tech project in 2011, all countries in the world began to guide the transformation of enterprises with the goal of smart factories in order to maintain their advantages. The technology of Virtual metrology plays an important role in the semiconductor field, and Virtual metrology can help improve product yield, reduce measurement cost, increase output rate and upgrade product measurement from sampling measurement to comprehensive measurement; Virtual metrology has developed to a certain extent in the industry, and each company has developed its own architecture, but the currently used models are mostly mathematical models that are manually set. It takes a lot of time to manually set the parameters. The selection of relevant parameters also depends on the selection of the expertise of the process personnel. It is relatively easy to cause personal error and cannot be complicated. And the mathematical models can’t predict complicated parameters.
Therefore, this study proposes an improved approach based on the existing architecture and replaces the existing manual setting models with deep learning models to reduce labor costs reduce and the model's reliance on process expertise, and support complex measurement parameter prediction. In this study, Pure NN is combined with Rule Based Improved NN plus Weight NN's deep learning model architectures. The average error value of deep learning mathematical model is 0.044 compared with the average error value of manually set mathematical model of 0.05, which has higher accurate prediction. As a result, it proves that the feasibility of the manual setting mathematical models is replaced by deep learning models.

[1] 王國維 (2016)。《適用於工具機產業之全自動虛擬量測系統自動建模機制》。國立成功大學製造資訊與系統研究所碩士論文，未出版，台南市。
[2] 吳偉民 (2012)。《虛擬量測精度之提升機制》。國立成功大學製造資訊與系統研究所博士論文，未出版，台中市。
[3] 杜佳駿 (2014)。《基於私有雲技術精進全自動虛擬量測系統》。國立成功大學製造資訊與系統研究所碩士論文，未出版，台南市。
[4] 吳竺潔 (2013)。《適用於全自動虛擬量測系統之智慧型取樣決策機制》。國立成功大學製造資訊與系統研究所博士論文，未出版，台南市。
[5] 林彥璋 (2004)。《一個適用於半導體業網路式診斷應用之介面的通用型嵌入式裝置》。國立成功大學製造資訊與系統研究所博士論文，未出版，台中市。
[6] 林嶸銓 (2005)。《通用型虛擬量測機制與系統》。國立成功大學製造資訊與系統研究所博士論文，未出版，台中市。
[7] 林献祥 (2010)。《應用先進製程控制虛擬量測技術於LED磊晶製程波長預測》。國立交通大學管理學院碩士在職專班資訊管理組研究所碩士論文，未出版，新竹市。
[8] 柯璟銘 (2006)。《化學機械研磨之虛擬量測與製程控制》。國立交通大學機械工程系研究所碩士論文，未出版，新竹市。
[9] 高易中 (2010)。《植基於主記憶體型資料庫技術之新式全自動化虛擬量測架構》。國立成功大學製造資訊與系統研究所碩士論文，未出版，台南市。
[10] 陳詩絢 (2012)。《二階段變數選取方法應用於半導體製程的虛擬量測之研究》。國立中興大學資訊科學與工程學系研究所碩士論文，未出版，台中市。
[11] 梁志翔 (2006)。《虛擬量測自變數之篩選法則》。國立成功大學製造資訊與系統研究所碩士論文，未出版，台南市。
[12] 許智誠 (2014)。《適用於全自動虛擬量測系統的新穎量測資料品質評估架構》。國立成功大學製造資訊與系統研究所碩士論文，未出版，台南市。
[13] 曾煒傑 (2014)。《具容錯轉移與負載平衡能力之全自動虛擬量測佈署系統》。國立成功大學製造資訊與系統研究所碩士論文，未出版，台南市。
[14] 黃暄恆 (2013)。《適用於全自動虛擬量測系統之智慧型參數篩選機制》。國立成功大學製造資訊與系統研究所博士論文，未出版，台南市。
[15] 楊志偉 (2007)。《類神經網路於虛擬量測系統之應用》。國立中興大學資訊科學與工程學系研究所碩士論文，未出版，台中市。
[16] 葉耀智 (2007)。《類神經虛擬量測之參數篩選與精度精進》。國立成功大學製造資訊與系統研究所碩士論文，未出版，台南市。
[17] 楊逸群 (2014)。《具備全自動虛擬量測功能的鋁輪圈加工自動化系統》。國立成功大學製造資訊與系統研究所碩士論文，未出版，台南市。
[18] 葉雅綸 (2016)。《以偏最小平方法建構光阻膜厚之虛擬量測模式及其實證研究》。國立清華大學工業工程與工程管理學系研究所碩士論文，未出版，新竹市。
[19] 鄭芳田（2013）。 “全自動虛擬量測。” 科學發展。490。
[20] 劉鈞霆 (2010)。《ART2參數自動尋優機制》。國立成功大學製造資訊與系統研究所博士論文，未出版，台南市。
[21] 顏羅桑 (2007)。《虛擬量測資料品質評估指標》。國立成功大學製造資訊與系統研究所碩士論文，未出版，台南市。
[22] I. Baytas, C. Xiao, X. Zhang, F. Wang, A. Jain, and J. Zhou, “Patient Subtyping via Time-Aware LSTM Networks,” Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2017), pp. 65-74, 2017.
[23] H. Cheng, M. Ispir, R. Anil, Z. Haque, L. Hong, V. Jain, X. Liu, H. Shah, L. Koc, J. Harmsen, T. Shaked, T. Chandra, H. Aradhye, G. Anderson, G. Corrado, and W. Chai, “Wide & Deep Learning for Recommender Systems,” Proceedings of the 1st Workshop on Deep Learning for Recommender Systems (DLRS 2016), pp. 7-10, 2016.
[24] F.-T. Cheng, H.-C. Huang, and C.-A. Kao, “Dual-Phase Virtual Metrology Scheme, IEEE Transactions on Semiconductor Manufacturing, vol. 20, no. 4, pp. 566-571, November 2007.
[25] F.-T. Cheng, Y.-T. Chen, Y.-C. Su, and D.-L. Zeng, “Evaluating Reliance Level of a Virtual Metrology System, IEEE Transactions on Semiconductor Manufacturing, vol. 21, no. 1, pp. 92-103, February 2008
[26] F.-T. Cheng, H.-C. Huang, and C.-A. Kao, “Developing an Automatic Virtual Metrology System, IEEE Trans. on Automation Science and Engineering, vol. 9, no. 1, pp. 181-188, Jan. 2012.
[27] F.-T. Cheng, H. Tieng, H.-C. Yang, M.-H. Hung, Y.-C. Lin, C.-F. Wei, and Z.-Y. Shieh, “Industry 4.1 for Wheel Machining Automation, in the 2016 IEEE International Conference on Robotics and Automation (ICRA 2016), Stockholm, Sweden, May 16-21, 2016.
[28] Y.-C. Chang and F.-T. Cheng, “Application Development of Virtual Metrology in Semiconductor Industry,” in Pro. of the 31st Annual Conference of the IEEE Industrial Electronics (IECON 2005), Raleigh, North Carolina, USA, pp. 124-129, November 2005.
[29] P.-H. Chen, S. Wu, J.-S. Lin, F. Ko, H. Lo, J. Wang, C.-H. Yu, and M.-S. Liang, “Virtual Metrology: a Solution for Wafer to Wafer Advanced Process Control,” in Proc. 2005 IEEE International Symposium on Semiconductor Manufacturing, San Jose, CA ,USA, pp.155-157, Sept. 2005.
[30] N. Du, H. Dai, R. Trivedi, U. Upadhyay, M. Gomez-Rodriguez, and L. Song, “Recurrent Marked Temporal Point Processes,” Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2016), pp. 1555-1564, 2016.
[31] Xavier Glorot, and Yoshua Bengio, “Understanding the Difficulty of Training Deep Feedforward Neural Networks”, International Conference on Artificial Intelligence and Statistics (AISTATS), 2010.
[32] Y.-T. Huang and F.-T. Cheng, “Automatic data quality evaluation for the AVM system, IEEE Transactions on Semiconductor Manufacturing, vol. 24, no. 3, pp.445-454, August 2011.
[33] Himmel, C.D., Kim, B.W., and May, G.S., “A COMPARISON OF STATISTICALLY -BASED AND NEURAL NETWORK MODELS OF PLASMA ETCH BEHAVIOR,” IEEE/SEMI Int''l Semiconductor Manufacturing Science Symposium 1992.
[34] Y.-T. Huang, F.-T. Cheng, and Y.-T. Chen, “Importance of data quality in virtual metrology,” in Proc. of the 32nd Annual Conference of the IEEE Industrial Electronics Society (IECON 2006), Paris, France, pp.3727-3732, Nov. 2006
[35] Q. Liu, S. Wu, L. Wang, and T. Tan, “Predicting the next location: a recurrent model with spatial and temporal contexts,” Proceedings of the 13th AAAI Conference on Artificial Intelligence (AAAI 2016), pp.194-200, 2016.
[36] T.-H. Lin, M.-H. Hung, R.-C. Lin, and F.-T. Cheng, “A Virtual Metrology Scheme for Predicting CVD Thickness in Semiconductor Manufacturing, in Proc. 2006 IEEE International Conference on Robotics and Automation, Orlando, Florida, U.S.A., pp.1054-1059, May 2006.
[37] J. Manotumruksa, C. Macdonald, and I. Ounis, “A Deep Recurrent Collaborative Filtering Framework for Venue Recommendation,” Proceedings of the 2017 ACM on Conference on Information and Knowledge Management (CIKM 2017), pp. 1429-1438, 2017.
[38] Sebastian Ruder, “An overview of gradient descent optimization algorithms.”: http://sebastianruder.com/optimizing-gradient-descent/
[39] W.-M. Wu, F.-T. Cheng, T.H. Lin, D.-L. Zeng, and J.-F. Chen, “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, April 2011.
[40] Y. Zhu, H. Li, Y. Liao, B. Wang, Z. Guan, H. Liu, and D. Cai, “What to Do Next: Modeling User Behaviors by Time-LSTM,” Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI 2017), pp. 3602-3608, 2017.