在批式反應器於操作之時，由於無適當之線上分析儀器可量測其即時產物品質，而導致其在操作時往往無法達到最佳之能源效益或是產品純度之要求等之問題。本研究乃以近年來被多方利用之”類神經網路” (artificial neural networks,簡稱ANN)技術來架構一適用於批式反應器之產物品質估測器；此估測器乃利用反應器溫度與實驗方法來估測產物之即時組成。
研究結果發現，ANN網路若於訓練時所考慮的變化狀況越完備，則於實際操作時所獲得的結果將會更具準確性；亦即以ANN做產物品質估測時之成功的重要因素之一，乃是訓練組數據收集之完備否。並由研究結果可知，以ANN產物品質估測器預測之數據來預測批式反應器之即時產物品是可行的。

Although composition analyzers, like on-line gas chromatorgraphy (on-line GC), have been used in the process industries for a long time, they are seldom found in the batch reactor process control. The use of inferential variables (like temperatures) to estimate process polymer quality in place of direct measurements is usually desired for plant engineers. The batch reactor has been reported a dynamic, nonlinear system; it is more complex and difficult to predict polymer qualities in a batch emulsion reactor through the use of temperature measurements.
The artificial neural networks (ANN) is composed of nets of nonlinear basis functions; it has the ability to evolve a good process model from experimental data which requires very little or no knowledge of first principles. In addition, it has the ability of learning and prediction for nonlinear model, and has therefore been used to identify the process dynamics nonparametrically. The main purpose of this study is using stacked and recurrent ANN to estimate the polymer qualities in a batch emulsion reactor. Several techniques, which include using laboratory data for ANN, have been proposed. Simulation results have demonstrated that the proposed approach can successfully apply to the building of soft sensors for a batch emulsion polymerization reactor.

中文摘要………………………………………………...……………III
英文摘要………………………………………………...……………IV
誌謝…………………………………………………………………...…V
目錄……………………………………………...……………………..VI
表目錄………………………………………………………………VIII
圖目錄………………………………………………...…………IX
符號說明……………………………………………………..……….XI
參數表…………………………………………………………..XV
第一章 緒論……………………………………………………………1
第二章 文獻回顧………………………………………………………3
第三章 乳化聚合反應器之動態模擬…………..……..………………9
反應器質量均衡計算…….……………………………….……10
反應器能量均衡計算………………..………………….…..18
EPM之Matlab程式模擬………………..………………….…..19
第四章 類神經網路之基本原理……………………………………..26
類神經網路簡介………………………………..………………..26
加權值搜索法則………………………….…………..………….29
雙隱藏層結構……………………………………...…………….31
回流與堆疊式網路……………………………..…….………….33
第五章 產物品質估測器之訓練與測試……………………..……..38
數據收集………………………………………………...……….38
網路之訓練與測試結果………………………………………40
第六章 結論…………………………………………………………..63
參考文獻………………………………………………………….…….64
簡歷……………………………………………………………………..65

陳文川與黃琦聰,”應用類神經網路於批示蒸餾塔之推論控制,”程序系統工程研討會, 128, 2003.
Baddar, E. E. and B. W. Brooks,” Start-Up Procedures for Continuous Flow Emulsion Polymerization Reactors,”Chem. Eng. Sci., 39, 1499 (1984).
Baughman, D. R. and Y. A. Liu,”Neural Networks for Bioprocessing and Chemical Engineering,” Academic Press, Inc., San Diego (1995).
Clarke-Pringle, T. L. and J. F. MacGregor,” Optimization of Molecular-Weight Distribution Using Batch-to-Batch Adjustments,” Ind. Eng. Chem. Res ., 37, 3660 (1998).
Congalidis, J. P. and J. P. Richards,” Process Control of Polymerization Reactors: An ndustrial Perspective,” Poly. Reactor Eng., 6, 71 (1998).
Congalidis, J. P., J. P. Richards and W. H. Ray,” Feedforward and Feedback Control of a Solution Copolymerization Reactor,” AICHE J., 35, 891 (1998).
Gilbert, R. G.,” Emuulsion Polymersion. A Mechanistic Appproach,” Academic Press Limited, London, 1995.
Erdogan, S., M. Alpbaz and A. R. Karagoz,” The Effect of Operational on the Performance of Batch Polymerization Reactor Control,” Chem. Eng. J., 86, 259 (2002).
Hansen, F. K., and J. Ugelstad,” Particle Nucleation in Emulsion Polymerization. I. A theory for Homogeneous Nucleation,” J. Polym. Sci. Polym. Chem. Ed., 16, 1953 (1978).
Horn, J,” Trajectory Tracking of a Batch Polymerization Reactor Based on Input-Output-Linearization of a Neural Process Model,” Comp. Chem. Eng., 25, 1561 (2001).
Kiparissides, C.,” Polymerization Reactor Modeling: A Review of Recent Developments and Future Directions,” Chem. Eng. Sci ., 51, 1637 (1996).
Krothapally , M. and S. Palanki,” A Neural Network Strategy for Batch Process Optimization,” Comp. Chem. Eng., 21, S463 (1997).
Machado, R. A. F. and A. Bolzan,” Control of Batch Suspension Polymerization Reactor,” Chem. Eng. J., 70, 1 (1998).
NeuralWare, Inc. Neural Computing: A Techanical Handbook for Professional II/PLUS and NeuralWorks Explorer, Pittsburgh, PA (1993).
Ng, C. W. and M. A. Hussain,” Hybrid Neural Network－Prior Knowledge Model in Temperature Control of a Semi-batch Polymerization Process,” Chem. Eng. Proce., 40, 4525 (2001).
Nomura, M. and K. Fujita,” On the Prediction of the Rate of Emulsion Copolymerization and Copolymer Composition,” Makromol. Chem. Suppl., 10, 105 (1985).
Ottewill, R. H.,”Emulsion Polymerization,” I. Piirma, Ed., Academic, New York (1982).
Richards, J. P., J. P. Congalidis and R. G.. Gilbert,” Mathematical Modeling of Emulsion Copolymerization Reactors,” J. Appl. Polym. Sci., 37, 2727 (1989).
Smith, W.V. and R. H. Ewart,” Kinetics of Emulsion Polymerization,”. J. Chem. Phys., 16, 592 (1948).
Tina, Y., J. Zhang and J. Morris,” Modeling and Optimal Control of a Batch Polymerisation Reactor Using a Hybrid Stacked Recurrent Neural Networks Model,” Ind. Eng. Chem. Res., 40, 4525 (2001).
Tina, Y., J. Zhang and J. Morris,” Optimal Control of a Batch Emulsion Copolymerisation Reactor Based on Recurrent Neural Networks Models,” Chem. Eng. Proce., 41, 531 (2002).
Tina, Y., J. Zhang and J. Morris,” Dynamic On-Line Reoptimization Control of a Batch MMA Polymerization Reactor Using Hybrid Neural Network Models,” Chem. Eng. Technol., 27, 1030 (2004).
Wang, Z. L., F. Pla and J. P. Corriou,” Nonliear Adaptive Control of Batch Styrene Polymerization,” Chem. Eng. Sci ., 5, 2081 (1995).
Zhang, L., E. B. Martin, A. J. Morris and C. Kiparissides,” Inferential Estimation of Polymer Quality Using Stacked Neural Networks,” Comput. Chem. Eng., 21, S1025 (1997).
Zhang, L.,A. J. Morris, E. B. Martin and C. Kiparissides,” Prediction of Polymer Quality in Batch Polymerisation Reactors Using Robust Neural Networks,” Chem. Eng. J., 69, 135 (1998).
Zhang, J. ,E. B. Martin and A. J. Morris,” Long-term Predictive Models based upon Mixed Order Locally Recurrent Neural Networks,” Comput. Chem. Eng., 22, 7-8, 1051 (1998) .
Yang, S. H., P. W. H. Chung and B. W. Brooks,” Multi-Stage Modeling of a Semi-Batch Polymerization Reactor Using Artificial Neural Networks,” Trans. IChE., 77, 779 (1999).
Yeh, T. M., M. C. Huang and C. T. Huang,” Estimate of Process Compositions and Plantwide Control from Multiple Secondary measurements Using Artificial Neural Networks,” Comput. Chem. Eng., 27, 55 (2003).
You, Y. and M. Nikolaou,” Dynamic Process Modeling with Recurrent Neural Networks,” AICHE J., 39, 1654(1993).