本研究以乙酸異丙酯反應蒸餾製程作為載體，探討在工業4.0的生產模式下，如何實現製程監測、預測及導航之功能。本研究先以Aspen Plus v9.0對程序建立第一原理模型，再以Aspen Plus Dynamics v9.0產生用以訓練類神經網路模型的數據。類神經網路模型的輸入變數有5，分別為:異丙醇進料流量、第12板溫度控制器之設定點、第3板溫度控制器之設定點、異丙醇進料中之異丙醇莫爾分率及醋酸進料中之醋酸莫爾分率;而模型的輸出變數則為主產物乙酸異丙酯於側流中之莫爾分率及分相槽水相中的水之莫爾分率。類神經網路則藉由Matlab建立。其架構為1輸入層，1隱藏層及1輸出層，其中，隱藏層裡有14個神經元。
本研究分別以傳統的PID控制及高階程序控制中的模式預測控制進行製程導航之設計。此外，於控制研究中探討數種不同的情境，包含所有產品之濃度(控制變數)皆由線上濃度量測儀器提供、只由虛擬模型(類神經網路)提供以及大部分數據由虛擬模型提供，但每隔一段時間皆有一筆真實量測之數據對模型進行校正。並且，溫度控制氣設定點(操作變數)調整之速度亦被考慮進本研究中，分別為10、30、60分鐘調動一次操作變數。根據控制響應之結果顯示，使用模式預測控制之控制性能較傳統PID控制器來的較佳，且穩定時間也較短。於12個策略中，以每4小時校正一次控制變數，且操作變數調整速度為每1小時一次之操作為最佳之策略。
本研究亦探討老化現象對製程及控制架構之影響。本研究探討在觸媒失活下，探討原始的控制架構下之製程暫態行為，並對此提出5個控制策略。根據響應結果，於一段時間後產品之純度皆無法維持在控制點上，於此5策略中，最長的操作天數約為270天，然而此策略無法排除干擾。若製程於1年內皆無擾動進入系統中，可以不需更換觸媒，倘若會有干擾發生時，則需每6個月更換一次觸媒。

In this thesis, the isopropyl-acetate (IPAc) production via reactive distillation (RD) process is taken to observe the control performance with the assistant of the virtual model. The artificial neural network (ANN) was trained to be the virtual model, and the Aspen Plus Dynamics was considered as the real plant. The inputs of the ANN model contain the feed flowrate of isopropyl alcohol (IPA) (FIPA), the setpoints of the temperature controllers (〖TC〗_12^sp, 〖TC〗_3^sp), and the feed composition of IPA and acetate acid (HAc) (x_OH^F, x_Ac^F). Then, the corresponding outputs are the IPAc mole fraction in the product (XIPAc) and the water mole fraction in the aqueous phase of the decanter (XWater). In order to maintain product purity, the model predictive control (MPC) was utilized to control the product concentration. In this process, the control variables (CVs) are the outputs of the ANN model, and the manipulated variables (MVs) are the setpoints of the temperature controllers (〖TC〗_12^sp, 〖TC〗_3^sp).
In reality, the catalyst activity would become smaller with time. However, the virtual model would not have the aging phenomenon if the model is built under the steady-state. At length, the model mismatches between the model and process would become greater if the virtual model does not be adjusted. To this end, this study focused on the updating method for the models which are established under the steady condition.
There are 5 strategies would be proposed in this thesis. According to the results, the on-spec products could be generated for 6 months if the model had been updated. If the process does not have the disturbances into the system within 1 year, there is no need to replace the catalyst. However, if there are any disturbances, the catalyst should be replaced per 6 months.

中文
1) 李宜達，「控制系統設計與模擬 – 使用Matlab/Simulink」，全華圖書，2011
2) 李昇育，「複合式薄膜反應蒸餾製程於醋酸酯類系統之應用」，國立台灣大學化學工程學研究所，碩士論文，2016
3) 李豪業，「非線性不穩定程序之多重現性模式預測控制」，長庚大學化學與材料工程研究所，碩士論文，2000
4) 林義皓，「第一型糖尿病血糖動態模式的建立與應用」，國立台灣科技大學化學工程研究所，碩士論文，2008
5) 楊宗樺，「類神經網路之動態估測器於高壓共聚合反應之應用」，國立台灣大學化學工程學研究所，碩士論文，2007
6) 楊儒鑫，「使用類神經網路作批次式程序之品質控制 – 醋酸乙烯乳化聚合之研究」，國立清華大學化學工程所，碩士論文，1993
7) 董欣華，「類神經網路在非線性系統模式化的應用」，國立臺灣工業技術學院化學工程技術研究所，碩士論文，1993
8) 賴一寬，「蒸餘曲線圖與沸點排序在反應蒸餾程序設計上的應用」，國立台灣大學化學工程學研究所，博士論文，2010
9) 羅華強，「類神經網路 – Matlab的應用」，高力圖書，2011

英文
1) Agreda, V. H. and Partin, L. R. (1984) Reactive Distillation Process for the Production of Methyl Acetate. U.S. Patent 4435595.
2) Al-Arfaj, M. A. and Luyben, W. L. (2004) Plantwide Control for TAME Production UsingReactive Distillation. AIChE Journal, 50 (7), 1462-1473.
3) Al-Arfaj, M. and Luyben, W. L. (2000) Comparison of Alternative Control Structures for an Ideal Two-Product Reactive Distillation Column. Ind. Eng. Chem. Res, 39, 3298-3307.
4) Balasubramhanya, L. S. and Doyle, F. J. (2000) Nonlinear model-based control of a batch reactive distillation column. J. Process. Contr., 10, 209-218.
5) Barbosa, D. and Doherty, M. F. (1988a) Design and minimum Reflux Calculations for Single-Feed Multicomponent Reactive Distillation Columns. Chem. Eng. Sci, 43, 1523-1537.
6) Barbosa, D. and Doherty, M. F. (1988b) Design and minimum Reflux Calculations for Double-Feed Multicomponent Reactive Distillation Columns. Chem. Eng. Sci, 43, 2377.
7) Barton, R. S. and Himmelblau, D. M. (1997) On-line Prediction of Polymer Product Quality in an Industrial Reactor using Recurrent Neural Networks. Proceedings of International Conference on Neural Networks (ICNN'97), 111-114.
8) Beckhaus, A. A. (1921) Apparatus for the Manufacture of Esters. U.S. Patent 1400849A.
9) Cardoso, M. F., Salcedo, R. L., Azevedo, S. F. D., Barbosa, D. (2000) Optimization of Reactive Distillation Processes with Simulated Annealing. Chem. Eng. Sci, 55, 5059-5078.
10) Chen, D.Y., Weng, K. C., Wang, S. J., Lee, H. Y. (2015) Design of Diphenyl Carbonate Process via Reactive Distillation Configuration. Chem. Eng. Trans, 45, 1195-1200.
11) Chen, F., Huss, R. S., Malone, M. F., Doherty, M. F. (2000) Simulation of Kinetic Effects in Reactive Distillation. Comput. Chem. Eng, 24, 2457-2472.
12) Ciric, A. R. and Miao, P. (1994) Steady State Multiplicities in an Ethylene Glycol Reactive Distillation Column. Ind. Eng. Chem. Res, 33, 2738-2748.
13) Cutler, C. R., & Ramaker, B. L. (1979). Dynamic matrix control – a computer control algorithm. AICHE national meeting, Houston, TX, April 1979.
14) Doherty, M. F. and Buzard, G. (1992) Reactive Distillation by Design. Chem. Eng. Res. Des, 70. 448-458.
15) Froisy, J. B. (1994). Model predictive control: Past, present and future. ISA Transactions, 33, 235-243.
16) Froisy, J. B. (2006) Model predictive control – Building a bridge between theory and practice. Comput. Chem. Eng., 30, 1426-1435.
17) Gadewar, S. B., Malone, M. F., Doherty, M. F. (2002) Feasible region for a countercurrent cascade of vapor‐liquid CSTRS. AIChE Journal, 48 (4), 800-814.
18) García, C. E., Prett, D. M., & Morari, M. (1989). Model predictive control: Theory and practice – a survey. Automatica, 25 (3), 335-348.
19) Hagan, M. T., Demuth, H. B., Beale, M. (1996) Neural Network Design. PWS Publishing Company.
20) Harmsen, G. J. (2007) Reactive Distillation: The Front-Runner of Industrial Process Intensification: A full Review of Commercial Applications, Research, Scale-up, Design and Operation. Chem. Eng. Process, 46, 774-780.
21) Himmelblau, D. M. (2000) Applications of Artificial Neural Networks in Chemical Engineering. Chem. Eng., 17, 373-392.
22) Hussain, M. A. (1999) Review of the applications of neural networks in chemical process control – simulation and online implementation. Artificial Intelligence in Engineering, 13, 55-68.
23) Jacobs, R. and Krishna, R. (1993) Multiple Solutions in Reactive Distillation for Methyl Tert-Butyl Ether Synthesis. Ind. Eng. Chem. Res, 32, 1706-1709.
24) Kalman, R. E. (1960a). Contributions to the theory of optimal control. Bulletin de la Societe Mathematique de Mexicana, 5, 102-119.
25) Kalman, R. E. (1960b). A new approach to linear filtering and prediction problems. Transactions of ASME, J. Basic Eng., 87, 35-45.
26) Katariya, A., Freund, H., Sundmacher, K. (2009) Two-Step Reactive Distillation Process for Cyclohexanol Production from Cyclohexene. Ind. Eng. Chem. Res, 48, 9534-9545.
27) Kawathekar, R. and Riggs, J. B. (2007) Nonlinear model predictive control of a reactive distillation column. Control Eng. Pract., 15, 231-239
28) Kaymak, D. B. and Luyben, W. L. (2004) Design of Distillation Columns with External Side Reactors. Ind. Eng. Chem. Res, 43, 8049-8056.
29) Ke, W., Huang, D., Yang, F., Jiang, Y. (2012) Soft sensor development and applications based on LSTM in deep neural networks. 2017 IEEE Symposium Series on Computational Intelligence (SSCI), Honolulu, HI, USA.
30) Khaledi, R. and Young, B. R. (2005) Modeling and Model Predictive Control of Composition in an ETBE Reactive Distillation Column. Ind. Eng. Chem. Res., 44, 3134-3145.
31) Kumar, A. S. and Ahmad. Z. (2012) Model Predictive Control (MPC) and its Current Issues in Chemical Engineering. Chem. Eng. Comm., 199 (4), 472-511.
32) Lai, I. K., Hung, S. B., Hung, W. J., Yu, C. C., Lee, M. J., Huang, H. P. (2007) Design and control of reactive distillation for ethyl and isopropyl acetates production with azeotropic feeds. Chem. Eng. Sci, 62, 878-898.
33) Lee J., Yoon, J., Yang, E., Hwang, S. J. (2017) Lifelong Learning with Dynamically Expandable Networks. ICLR’18. Vancouver, Canada.
34) Lee, H. Y., Li, S. Y., Chen, C. L. (2016) Evolutional Design and Control of the Equilibrium-Limited Ethyl Acetate Process via Reactive Distillation-Pervaporation Hybrid Configuration. Ind. Eng. Chem. Res., 55, 8802-8817.
35) Lee, J. H. (2011) Model Predictive Control: Review of the Three Decades of Development. Int. J. Control Autom., 9 (3), 415-424.
36) Lightbody, G. and Irwin, G. W. (1995) A novel neural internal model control structure. Proc Am Control Conf, 350-354.
37) MacMurry, J. C. and Himmelblau, J. C. (1995) Modeling and Control of a Packed Distillation Column Using Artificial Neural Networks. Comput. Chem. Eng., 19 (10), 1077-1088.
38) Megan, L. and Cooper, D. J. (1995) A Neural Network Strategy for Disturbance Pattern Classification and Adaptive Multivariable Control. Comput. Chem. Eng., 19 (2), 171-186.
39) Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K. (2014) Recurrent Models of Visual Attention. Advances in Neural Information Processing Systems 27 (NIPS 2014), Montréal, Canada.
40) Narendra, K. S. and Parthasarathy, K. (1990) Identification and control of dynamical systems using neural networks. IEE Proc Neural Networks, 1,4-27.
41) Okasinski, M. J. and Doherty M. F. (1998) Design Method for Kinetically Controlled. Staged Reactive, Ind. Eng. Chem. Res, 37, 2821-2834.
42) Olesen, D. H. (2012) Tuning Methods for Model Predictive Controllers. Doctor Thesis. Informatics and Mathematical Modelling, Technical University of Denmark.
43) Psichogios, D. C., Ungar, L. H. (1992) A Hybrid Neural Network-First Principles Approach to Process Modeling. AIChE J., 38, 1499-1511.
44) Qin, S. J. and Badgwell, T. A. (1997) An Overview of Industrial Model Predictive Control Technology. AIChE Symposium Series.
45) Qin, S. J. and Badgwell, T. A. (2003) A survey of industrial model predictive control technology. Control Eng. Pract., 11, 733-764.
46) Ravi Chandra, P. V. S. and Venkateswarlu Ch. (2007) Multistep model predictive control of ethyl acetate reactive distillation column. Indian Journal of Chemical Technology, 14, 333-340.
47) Richalet, J., Rault, A., Testud, J. L., & Papon, J. (1976). Algorithmic control of industrial processes. 4th IFAC symposium on identification and system parameter estimation, 1119-1167.
48) Richalet, J., Rault, A., Testud, J. L., & Papon, J. (1978). Model predictive heuristic control: Applications to industrial processes. Automatica, 14, 413-428.
49) Sanner, R. W. and Slotine, J.-J. E. (1992) Gaussian networks for direct adaptive control. IEEE Trans. Neural Netw., 3 (6), 837-863.
50) Seborg, D. E., Edgar, T. F., Mellichamp, D. A., Doyle, F. J. (2017) Process Dynamics and Control. Wiley.
51) Sharma, N. and Singh, K. (2012) Model predictive control and neural network predictive control of TAME reactive distillation column. Chem. Eng. Process., 59, 9-21.
52) Spielberg, S. P. K., Gopaluni, R. B., Loewen, P. D. (2017) Deep Reinforcement Learning Approaches for Process Control. 6th International Symposium on Advanced Control of Industrial Processes (AdCONIP), 201-206.
53) Su, H. T. and McAvoy, T. J. (1992) Long-Term Predictions of Chemical Processes Using Recurrent Neural Networks: A Parallel Training Approach. Ind, Eng. Chem. Res., 31, 1338-1352.
54) Tang, Y T., Huang, H. P. and Chien, I. L. (2003) Design of a Compelete Ethyl Acetate Reactive Distillation System. J. Chem. Eng. Japan, 36, 1352-1363.
55) Turner, P., Montague, G. A., Morris, A. J. (1995) Neural networks in dynamic process state estimation and nonlinear predictive control. Fourth IntConf Artificial Neural Networks, Cambridge, 284-289.
56) Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., Polosukhin, I. (2017) Attention Is All You Need. 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
57) Widrow, B. and Stearns, S. D. (1985) Adaptive Signal Processing. Prentice-Hall.
58) Willis, M. J., Montague, G. A., Morris, A. J. (1992) Artificial neural networks in process estimation and control. Automatica, 28 (6), 1181-1187
59) Wormsley, C. and Henry, J. (1994) A study of model predictive control for a distillation column. Am. Inst. Chem. Eng. Annual Nov. Meeting, San Francisco, CA, USA.
60) Younesi, A., Shayeghi, H., Moradzadeh, M. (2017) Application of reinforcement learning for generating optimal control signal to the IPFC for damping of low‐frequency oscillations. Int. Trans. Electr. Energy Syst., 28, 2488-2510.
61) Zhao, H., Sun, S., Jin, B. (2018) Sequential Fault Diagnosis Based on LSTM Neural Network. IEEE Access, 6, 12929-12939.