軟儀表企圖以可取得的其他操作變數及測量變數，預測難以直接量測的關鍵品質。標籤的關鍵品質歷史數據非常稀少，因此當建立數據驅動軟儀表模型，其對於製程物理行為的是否有合理泛化能力是需要被檢視的。此文中，使用了sequence to sequence神經網路建立觀察者-預測者模型。其中觀察者可以利用大量非標籤數據以監督方式學習，了解製程非線性動態行為。觀察者產生隱含記憶狀態並輸入至預測者，預測者以其他標籤品質數據訓練，透過隱含狀態及當前操作變數可預測關鍵品質。該模型運用在工業蒸餾塔案例，除了有好的預測能力，並有合理可解釋的製程程序增益現象，證明該模型可以充分使用非標籤數據了解製程物理動態行為。

Soft-sensors attempt to predict key quality variables that are infrequently available using sensor and manipulated variables that are readily available. Since only limited amount labeled data are available, there is always the concern whether underlying physics were captured so that the model can be reasonably extrapolated, A sequence-to-sequence model in the form of a nonlinear state-observer/encoder and predictor/decoder was proposed. The observer can be trained using a large amount of unlabeled data, but in a supervised manner in which the process dynamics was tracked. The encoder output and manipulated variables were used to train the quality predictor. The model was applied to product impurity predictions of an industrial column. Results show that good predictions and excellent consistency in the sign of estimated gains can be achieved even with limited amount of data. These findings indicated that the proposed sequence-to-sequence data-driven approach is able to capture the underlying physics of the process.

Abstract i
Acknowledgments ii
Table of contents iv
List of figures vi
List of tables ix
Chapter 1: Introduction .. 10
1.1. Research Background 10
1.2. Literature Review 11
1.2.1. Soft-sensor 11
1.2.2. Deep Learning and Neural Networks 12
1.3. Research Objectives 22
1.4. Structure of this Work 23
Chapter 2: Case Study: Distillation Column 24
2.1. Process Description 24
2.2. Data Description and Preprocessing 25
2.2.1. Preprocessing 25
2.2.2.Quality Historical Chart 26
Chapter 3: Proposed Soft-Senso 28
3.1. Artificial Neural Networks 28
3.2. Observer-Predictor soft sensor 30
3.3. Performance indices 32
Chapter 4: Results 34
4.1. Accuracy of sensor variables predictions 34
4.2. Distillate stream impurity 37
4.3. Bottom flow impurity 48
Chapter 5: Conclusion 61
References 62

1. 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.
2. 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.
3. 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.
4. 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.
5. 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.
6. 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.
7. 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.
8. 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.
9. Kadlec, P., Gabrys, B., and Strandt, S. (2009). Data-driven soft sensors in the process industry. Computers and chemical engineering, 33(4), 795-814.
10. 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.
11. 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.
12. Qin, S. J. (2014). Process data analytics in the era of big data. AIChE Journal, 60(9), 3092-3100.
13. 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.
14. 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.
15. Cybenko, G. (1989). Approximation by superpositions of a sigmoidal function. Mathematics of control, signals and systems, 2(4), 303-314.
16. Hornik, K., Stinchcombe, M., and White, H. (1989). Multilayer feedforward networks are universal approximators. Neural networks, 2(5), 359-366.
17. 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).
18. 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.
19. 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.
20. 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.
21. Ge, Z., and Song, Z. (2011). Semisupervised Bayesian method for soft sensor modeling with unlabeled data samples. AIChE Journal, 57(8), 2109-2119.
22. 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.
23. 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.
24. 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.
25. Ian Goodfellow, Y.B., Aaron Courville, Yoshua Bengio, Deep learning. 2016: MIT press.
26. Karpathy, A., Stanford University CS231n: Convolutional Neural Networks for Visual Recognition.
27. Nielsen, M.A., Neural Networks and Deep Learning. 2015: Determination Press.
28. Raschka, S., Introduction to Artificial Neural Networks and Deep Learning (Draft). 2018: University of Wisconsin-Madison.
29. Lecun, Y., et al., Gradient-based learning applied to document recognition. Proceedings of the Ieee, 1998. 86(11): p. 2278-2324.
30. Ruder, S., An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747, 2016.
31. Hermans, M. and B. Schrauwen, Training and analyzing deep recurrent neural networks, in Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 1. 2013, Curran Associates Inc.: Lake Tahoe, Nevada. p. 190-198.
32. Daniel Kosiorowski, D.M., Jerzy. P. Rydlewski, 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 (2018).
33. 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.
34. 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.
35. 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).
36. Bahdanau, D., Cho, K., and Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473.
37. 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.
38. 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.
39. Zhang, J., and Morris, A. J. (1999). Recurrent neuro-fuzzy networks for nonlinear process modeling. IEEE Transactions on Neural Networks, 10(2), 313-326.
40. 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.
41. 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.
42. 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.
43. 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.
44. 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.
45. Wu .H, Chou. C, Yuan. Y, Wong. D and Liu. Y, Process Monitoring Using a Sequence to Sequence Network, DDCLS2019, Dali, China, 2019.