為了讓工廠情況符合品質標準並改善工廠的控制動作使得工廠的操作條件能達到節能最佳化，需要利用品質變數(quality variable)、測量變數(sensor variable)、操作變數(manipulated variable)以及移動視窗法來建立軟儀表，本次研究中使用了類神經網路(ANN)來建立品質變數模型，測量變數模型則是使用了序列對序列模型(Seq2seq)。成果中ANN模型能夠準確的預測品質參數，並經由增益值方向正確率檢測擁有了正確的物理表現，而Seq2seq模型能夠準確的預測測量參數，但進行滾動測試(rolling test)時，模型的穩定性不佳，研究中開發了Seq2seq滾動模型，提升了Seq2seq模型的穩定性，ANN模型搭配Seq2seq滾動模型，就能夠使節能最佳化。

In order to make the factory meet the quality standards and improve the control actions of the factory so that the operating conditions of the factory can optimize energy saving. In this research, we use quality variable, sensor variable, manipulate variable and moving window to develop soft sensors. Artificial neural network is used to build quality variable model and sequence-to-sequence neural network is used to build sensor variable model. In the results, ANN model can predict quality variables precisely and ANN model gets good physical performance by gain consistency test. Seq2seq model can also predict sensor variables precisely, but Seq2seq model is very unstable in the rolling test. In this research, we develop Seq2seq rolling model to enhance the stability of Seq2seq model. When ANN model cooperate with Seq2seq rolling model we can optimize energy saving of the factory.

ABSTRACT I
摘要 II
目錄 III
圖目錄 V
表目錄 IX
第一章:緒論 10
第二章:案例分析:蒸餾塔 25
第三章:軟儀表建立 28
第四章:研究成果 35
第五章:結論 60
參考文獻 61

[1] J.Mohd Ali, M.A.Hussain, M.O.Tade, J.Zhang. (2015)Artificial Intelligence techniques applied as estimator in chemical process systems - A literature survey.Expert Syst. Appl. 42 5915–5931.
[2] C.Shang, F.Yang, D.Huang, W.Lyu. (2014) Data-driven soft sensor development based on deep learning technique, J. Process Control. 24, 223–233.
[3] Kano, M., and Nakagawa, Y. (2008). Data-based process monitoring, process control, and quality improvement: Recent developments and applications in steel industry. Computers and Chemical Engineering, 32(1-2), 12-24.
[4] Kano, M., and Ogawa, M. (2010). The state of the art in chemical process control in Japan: Good practice and questionnaire survey. Journal of Process Control, 20(9), 969-982.
[5] Liu, J., Chen, D. S., and Shen, J. F. (2010). Development of self-validating soft sensors using fast moving window partial least squares. Industrial and Engineering Chemistry Research, 49(22), 11530-11546.
[6] Chang, Y. J., Kang, Y., Hsu, C. L., Chang, C. T., and 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.
[7] Pan, T. H., Sheng, B. Q., Wong, D. S. H., and Jang, S. S. (2011). A virtual metrology system for predicting end-of-line electrical properties using a MANCOVA model with tools clustering. IEEE Transactions on Industrial Informatics, 7(2), 187-195.
[8] Haimi, H., Mulas, M., Corona, F., and Vahala, R. (2013). Data-derived soft-sensors for biological wastewater treatment plants: An overview. Environmental Modelling and Software, 47, 88-107.
[9] Shakil, M., Elshafei, M., Habib, M. A., and Maleki, F. A. (2009). Soft sensor for NOx and O2 using dynamic neural networks. Computers and Electrical Engineering, 35(4), 578-586.
[10] Lin, B., Recke, B., Knudsen, J. K., and Jørgensen, S. B. (2007). A systematic approach for soft sensor development. Computers and chemical engineering, 31(5-6), 419-425.
[11] Kadlec, P., Gabrys, B., and Strandt, S. (2009). Data-driven soft sensors in the process industry. Computers and chemical engineering, 33(4), 795-814.
[12] Souza, F. A., Araújo, R., and Mendes, J. (2016). Review of soft sensor methods for regression applications. Chemometrics and Intelligent Laboratory Systems, 152, 69-79.
[13] Prasad, V., Schley, M., Russo, L. P., and Bequette, B. W. (2002). Distillate property and distillateion rate control of styrene polymerization. Journal of Process Control, 12(3), 353-372.
[14] Qin, S. J. (2014). Process data analytics in the era of big data. AIChE Journal, 60(9), 3092-3100.
[15] Kadlec, P., Grbić, R., and Gabrys, B. (2011). Review of adaptation mechanisms for data-driven soft sensors. Computers and chemical engineering, 35(1), 1-24.
[16] Yuan, X., Wang, Y., Yang, C., Ge, Z., Song, Z., and Gui, W. (2017). Weighted linear dynamic system for feature representation and soft sensor application in nonlinear dynamic industrial processes. IEEE Transactions on Industrial Electronics, 65(2), 1508-1517.
[17] Cybenko, G. (1989). Approximation by superpositions of a sigmoidal function. Mathematics of control, signals and systems, 2(4), 303-314.
[18] Hornik, K., Stinchcombe, M., and White, H. (1989). Multilayer feedforward networks are universal approximators. Neural networks, 2(5), 359-366.
[19] Lu, Z., Pu, H., Wang, F., Hu, Z., and Wang, L. (2017). The expressive power of neural networks: A view from the width. In Advances in Neural Information Processing Systems (pp. 6231-6239).
[20] Gonzaga, J. C. B., Meleiro, L. A. C., Kiang, C., and Maciel Filho, R. (2009). ANN-based soft-sensor for real-time process monitoring and control of an industrial polymerization process. Computers and chemical engineering, 33(1), 43-49.
[21] Rani, A., Singh, V., and Gupta, J. R. P. (2013). Development of soft sensor for neural network based control of distillation column. ISA transactions, 52(3), 438-449.
[22] Shang, C., Yang, F., Huang, D., and Lyu, W. (2014). Data-driven soft sensor development based on deep learning technique. Journal of Process Control, 24(3), 223-233.
[23] Tian, Y., J. Zhang, and J. Morris, (2001).Modeling and optimal control of a batch polymerization reactor using a hybrid stacked recurrent neural network model. Industrial & engineering chemistry research. 40(21): p. 4525-4535.
[24] Xiong, Z. and J. Zhang, (2005) .A batch-to-batch iterative optimal control strategy based on recurrent neural network models. Journal of Process Control, 15(1): p. 11-21
[25] X. Yuan, B. Huang, Y. Wang, C. Yang and W. Gui.(2018)Deep Learning-Based Feature Representation and Its Application for Soft Sensor Modeling With Variable-Wise Weighted SAE," in IEEE Transactions on Industrial Informatics, vol. 14, no. 7, pp. 3235-3243
[26] Bowen Liu, B. Ramsundar, P. Kawthekar .(2017) Retrosynthetic Reaction Prediction Using Neural Sequence-to-Sequence Models ,ACS Cent. Sci. 2017, 3, 1103-1113
[27] Ge, Z., and Song, Z. (2011). Semisupervised Bayesian method for soft sensor modeling with unlabeled data samples. AIChE Journal, 57(8), 2109-2119.
[28] Yao, L., and Ge, Z. (2017). Deep learning of semisupervised process data with hierarchical extreme learning machine and soft sensor application. IEEE Transactions on Industrial Electronics, 65(2), 1490-1498.
[29] Shao, W., Yao, L., Ge, Z., and Song, Z. (2018). Parallel Computing and SGD-Based DPMM For Soft Sensor Development With Large-Scale Semisupervised Data. IEEE Transactions on Industrial Electronics, 66(8), 6362-6373.
[30] Liu, Y., Yang, C., Gao, Z., and Yao, Y. (2018). Ensemble deep kernel learning with application to quality prediction in industrial polymerization processes. Chemometrics and Intelligent Laboratory Systems, 174, 15-21.
[31] Ian Goodfellow, Y.B., Aaron Courville, Yoshua Bengio. (2016) Deep learning, MIT press.
[32] Karpathy, A., Stanford University CS231n: Convolutional Neural Networks for Visual Recognition.
[33] Nielsen, M.A. (2015). Neural Networks and Deep Learning, Determination Press.
[34] Raschka, S., (2018).Introduction to Artificial Neural Networks and Deep Learning (Draft), University of Wisconsin-Madison.
[35] Lecun, Y., et al. (1998). Gradient-based learning applied to document recognition. Proceedings of the Ieee, 86(11): p. 2278-2324.
[36] Ruder, S., An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747, 2016.
[37] Hermans, M. and B. Schrauwen.(2013) Training and analyzing deep recurrent neural networks, in Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 1. Curran Associates Inc.: Lake Tahoe, Nevada. p. 190-198.
[38] Daniel Kosiorowski, D.M., Jerzy. P. Rydlewski. (2018)Forecasting of a Hierarchical Functional Time Series on Example of Macromodel for Day and Night Air Pollution in Silesia Region: A Critical Overview. Central European Journal of Economic Modelling and Econometrics, 2017. 10: 53-73.
[39] Cho, K., Van Merriënboer, B., Bahdanau, D., and Bengio, Y. (2014). On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259.
[40] Chung, J., Gulcehre, C., Cho, K., and Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555.
[41] Sutskever, I., Vinyals, O., and Le, Q. V. (2014). Sequence to sequence learning with neural networks. In Advances in neural information processing systems (pp. 3104-3112).
[42] Bahdanau, D., Cho, K., and Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473.
[43] Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio. Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078.
[44] Kannan, A., Kurach, K., Ravi, S., Kaufmann, T., Tomkins, A., Miklos, B., and Ramavajjala, V. (2016, August). Smart reply: Automated response suggestion for email. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 955-964). ACM.
[45] Zhang, J., and Morris, A. J. (1999). Recurrent neuro-fuzzy networks for nonlinear process modeling. IEEE Transactions on Neural Networks, 10(2), 313-326.
[46] Lu, C. H., and Tsai, C. C. (2007). Generalized predictive control using recurrent fuzzy neural networks for industrial processes. Journal of process control, 17(1), 83-92.
[47] Pan, Y., and Wang, J. (2011). Model predictive control of unknown nonlinear dynamical systems based on recurrent neural networks. IEEE Transactions on Industrial Electronics, 59(8), 3089-3101.
[48] Sun, Q., and Ge, Z. (2018). Probabilistic sequential network for deep learning of complex process data and soft sensor application. IEEE Transactions on Industrial Informatics.
[49] Yuan, X., Li, L., and Wang, Y. (2019). Nonlinear dynamic soft sensor modeling with supervised long short-term memory network. IEEE Transactions on Industrial Informatics.
[50] Afram, A., Janabi-Sharifi, F., Fung, A. S., and Raahemifar, K. (2017). Artificial neural network (ANN) based model predictive control (MPC) and optimization of HVAC systems: A state of the art review and case study of a residential HVAC system. Energy and Buildings, 141, 96-113.
[51] Wu .H, Chou. C, Yuan. Y, Wong. D and Liu. Y. (2019 )Process Monitoring Using a Sequence to Sequence Network, DDCLS2019, Dali, China
[52] S.J.Pan, Q.Yang. (2010) A survey on transfer learning, IEEE Trans. Knowl. Data Eng. 22 1345–1359.