對於傳統製造產業而言，首件的生產是傳統工廠為了後續穩定量產必須的階段，然而作業員調機的準則往往仰賴經驗法則或是廣義的標準作業流程，當調整程序複雜時，生產合乎品質要求的首件將耗費大量的材料、時間與檢驗成本。2005年初虛擬量測的出現，使得生產之產品在尚未或無法進行實際量測的情況下，利用生產機台參數推估其產品品質，達到全檢的目標，加上近年來人工智慧愈來愈受到各界的重視，如：類神經網路、機器學習、深度學習等相關方法被廣泛應用到各個領域之中。極限梯度提升樹為2016 年學者提出之梯度集成樹方法，不僅支持分類模型，也支持迴歸模型，屬於一種加法樹，透過多棵樹的迭代來逐漸減少殘差。然而在虛擬量測的領域尚未有學者研究極限梯度提升樹算法，因此本篇研究將使用極限梯度提升樹作為主要的學習演算法進行研究，提出一套完整的虛擬量測系統，包含離線訓練以及線上測試，離線訓練包含模型一「預測首件生產品質特性」、模型二「預測首件調整內容」與透過模擬的方式利用貝氏最佳化尋找最佳的線性補正參數，線上偵測則依照首件生產的流程進行實測，發現模型一中以極限梯度提升樹預測表現最佳，模型二中隨機森林預測表現最穩定，然而以平均均方誤差為調參之目標函數時以極限梯度提升樹最佳。最後本研究於2019 年12 月至2020 年2 月期間實際測試10 次首件生產過程，以補正-虛擬量測系統表現最佳，相較過往的人工調整，可提升69.7%的調整效率，且可以縮短82.4%的首件生產時間。

For the manufacturing industries, first article production helps the enterprises to ensure the production process is correct and is an essential phase before they can go into mass production phase. However, it is worth noting that adjusting machine is usually based on rule of thumb or on the non-standard operating procedures. When adjustment process becomes complicated, some additional costs may become inevitable. In 2005, virtual metrology (VM) has been proposed to predict the quality characteristics based on the previous metrology information, instead of physical measurement. Recently artificial intelligence such as neural network, machine learning and deep learning has created a huge impact on different areas. Extreme Gradient Boosting Tree (XGBoost) developed in 2016 is a gradient ensemble tree method and can be embedded as a classification or regression model. However, XGBoost is seldom applied in virtual metrology field. In this study, we propose a novel virtual metrology system including off-line training phase and on-line detecting phase. Two models are proposed in off-line training phase using XGBoost, Random Forest (RF), Classification and Regression Tree (CART), Deep Neural Network (DNN), respectively. Firstly, the model 1 is used to predict the product quality index. If inferior product quality characteristics are expected, model 2 is applied to predict magnitude of machine adjustment for each index immediately. Consequently, we propose an offset compensation approach to improve predicting preformance by simulation and Bayesian optimization. XGBoost performs well in model 1 and RF performs good robustnees in model 2. We use an factory as a case study to apply our models from December 2019 to February 2020. The results show that using Virtual Metrology system with offset (VM-offset) has the best performance among different methods. In contrast to past manual adjustment, VM-offset can improve 69.7% of adjustment efficiency and reduce 82.4% of first article production time.

Andreasen, M. M., Kähler, S., Lund, T., & Swift, K. G. (1983). Design for assembly (pp. 95-127). London: Ifs Publications.
Bahl, S., Venkatesh, R. S., Craik, J., Bedi, R., Uriarte, H., & Srihari, K. (2002, July). Requirement specifications for an enterprise level collaborative, data collection, quality management and manufacturing tool for an EMS provider. In 27th Annual IEEE/SEMI International Electronics Manufacturing Technology Symposium (pp. 140-148). IEEE.
Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of Machine Learning Research, 13(Feb), 281-305.
Blum, A. L., & Langley, P. (1997). Selection of relevant features and examples in machine learning. Artificial Intelligence, 97(1-2), 245-271.
Breiman, L., Friedman, J., Olshen, R., & Stone, C. (1984). Classification and regression trees. Wadsworth Int. Group, 37(15), 237-251.
Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123-140.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32.
Carbery, C. M., Woods, R., & Marshall, A. H. (2018). A New Data Analytics Framework Emphasising Pre-processing in Learning AI Models for Complex Manufacturing Systems. In Intelligent Computing and Internet of Things (pp. 169-179). Springer, Singapore.
Chen, P., Wu, S., Lin, J., Ko, F., Lo, H., Wang, J., ...Liang, M. (2005, September). Virtual metrology: A solution for wafer to wafer advanced process control. In ISSM 2005, IEEE International Symposium on Semiconductor Manufacturing, 2005. (pp. 155-157). IEEE.
Chang, Y. J., Kang, Y., Hsu, C. L., Chang, C. T., & Chan, T. Y. (2006, July). Virtual metrology technique for semiconductor manufacturing. In The 2006 IEEE International Joint Conference on Neural Network Proceedings (pp. 5289-5293). IEEE.
Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794). ACM.
Dhaliwal, S., Nahid, A. A., & Abbas, R. (2018). Effective intrusion detection system using XGBoost. Information, 9(7), 149.
Ferreira, A., Roussy, A., & Condé, L. (2009, May). Virtual metrology models for predicting physical measurement in semiconductor manufacturing. In 2009 IEEE/SEMI Advanced Semiconductor Manufacturing Conference (pp. 149-154). IEEE.
Georganos, S., Grippa, T., Vanhuysse, S., Lennert, M., Shimoni, M., Kalogirou, S., & Wolff, E. (2018). Less is more: Optimizing classification performance through feature selection in a very-high-resolution remote sensing object-based urban application. GIScience & Remote Sensing, 55(2), 221-242.
Ham, S. (1978). The structural foam process as a cost reduction method. Journal of Cellular Plastics, 14(1), 42-44.
He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision (pp. 1026-1034).
Hinton, G. E., Osindero, S., & Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural computation, 18(7), 1527-1554.
Hung, M. H., Lin, T. H., Cheng, F. T., & Lin, R. C. (2007). A novel virtual metrology scheme for predicting CVD thickness in semiconductor manufacturing. IEEE/ASME Transactions on mechatronics, 12(3), 308-316.
Jin, H., Chen, X., Yang, J., Zhang, H., Wang, L., & Wu, L. (2015). Multi-model adaptive soft sensor modeling method using local learning and online support vector regression for nonlinear time-variant batch processes. Chemical Engineering Science, 131, 282-303.
Kanellopoulous, I. and Wilkinson, G. G. (1997). Strategies and best practice for neural network image classification. International Journal of Remote Sensing, 18(4), 711-725.
Kang, P., Kim, D., Lee, H. J., Doh, S., & Cho, S. (2011). Virtual metrology for run-to-run control in semiconductor manufacturing. Expert Systems with Applications, 38(3), 2508-2522.
Kim, M., Kang, S., Lee, J., Cho, H., Cho, S., & Park, J. S. (2017). Virtual metrology for copper-clad laminate manufacturing. Computers & Industrial Engineering, 109, 280-287.
Lenz, B., & Barak, B. (2013, January). Data mining and support vector regression machine learning in semiconductor manufacturing to improve virtual metrology. In 2013 46th Hawaii International Conference on System Sciences (pp. 3447-3456). IEEE.
Lenz, B., Barak, B., Mührwald, J., & Leicht, C. (2013, December). Virtual metrology in semiconductor manufacturing by means of predictive machine learning models. In 2013 12th International Conference on Machine Learning and Applications(Vol. 2, pp. 174-177). IEEE.
Lin, K. Y., Hsu, C. Y., & Yu, H. C. (2014). A virtual metrology approach for maintenance compensation to improve yield in semiconductor manufacturing. International Journal of Computational Intelligence Systems, 7(sup2), 66-73.
Lv, S., Kim, H., Zheng, B., & Jin, H. (2018). A Review of Data Mining with Big Data towards Its Applications in the Electronics Industry. Applied Sciences, 8(4), 582.
Marques, G., Gourc, D., & Lauras, M. (2011). Multi-criteria performance analysis for decision making in project management. International Journal of Project Management, 29(8), 1057-1069.
Nguyen, V., Gupta, S., Rana, S., Li, C., & Venkatesh, S. (2017, November). Regret for expected improvement over the best-observed value and stopping condition. In Asian Conference on Machine Learning (pp. 279-294).
Ouyang, Z., Sun, X., Chen, J., Yue, D., & Zhang, T. (2018). Multi-view stacking ensemble for power consumption anomaly detection in the context of industrial internet of things. IEEE Access, 6, 9623-9631.
Patel, H., Thakkar, A., Pandya, M., & Makwana, K. (2018). Neural network with deep learning architectures. Journal of Information and Optimization Sciences, 39(1), 31-38.
Pennella, C. R. (2006). Managing Contract Quality Requirements. ASQ Quality Press.
Quinlan, J. R. (1986). Induction of decision trees. Machine Learning, 1(1), 81-106.
Ringwood, J. V., Lynn, S., Bacelli, G., Ma, B., Ragnoli, E., & McLoone, S. (2009). Estimation and control in semiconductor etch: Practice and possibilities. IEEE Transactions on Semiconductor Manufacturing, 23(1), 87-98.
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985). Learning internal representations by error propagation (No. ICS-8506). California Univ San Diego La Jolla Inst for Cognitive Science.
Seide, F., Li, G., & Yu, D. (2011). Conversational speech transcription using context-dependent deep neural networks. In Twelfth annual conference of the international speech communication association.
Shahriari, B., Swersky, K., Wang, Z., Adams, R. P., & De Freitas, N. (2015). Taking the human out of the loop: A review of Bayesian optimization. Proceedings of the IEEE, 104(1), 148-175.
Sharma, D., Armer, H., & Moyne, J. (2012, May). A comparison of data mining methods for yield modeling, chamber matching and virtual metrology applications. In 2012 SEMI Advanced Semiconductor Manufacturing Conference (pp. 231-236). IEEE.
Snoek, J., Larochelle, H., & Adams, R. P. (2012). Practical bayesian optimization of machine learning algorithms. In Advances in Neural Information Processing Systems (pp. 2951-2959).
Terzi, M., Masiero, C., Beghi, A., Maggipinto, M., & Susto, G. A. (2017, September). Deep learning for virtual metrology: Modeling with optical emission spectroscopy data. In 2017 IEEE 3rd International Forum on Research and Technologies for Society and Industry (RTSI) (pp. 1-6). IEEE.
Timofeev, R. (2004). Classification and regression trees (CART) theory and applications. Humboldt University, Berlin.
Tsuda, T., Inoue, S., Kayahara, A., Imai, S. I., Tanaka, T., Sato, N., & Yasuda, S. (2015). Advanced semiconductor manufacturing using big data. IEEE Transactions on Semiconductor Manufacturing, 28(3), 229-235.
Williams, C. K., & Rasmussen, C. E. (2006). Gaussian Processes for Machine Learning (Vol. 2, No. 3, p. 4). Cambridge, MA: MIT press.
Zhang, D., Qian, L., Mao, B., Huang, C., Huang, B., & Si, Y. (2018). A data-driven design for fault detection of wind turbines using random forests and XGboost. IEEE Access, 6, 21020-21031.
Zhang, R., Li, B., & Jiao, B. (2019, April). Application of XGboost Algorithm in Bearing Fault Diagnosis. In IOP Conference Series: Materials Science and Engineering (Vol. 490, No. 7, p. 072062). IOP Publishing.
Zheng, H., Yuan, J., & Chen, L. (2017). Short-term load forecasting using EMD-LSTM neural networks with a Xgboost algorithm for feature importance evaluation. Energies, 10(8), 1168.