焦炭乾式淬火（Coke Dry Quenching , CDQ）系統是煉焦工場最重要之節能減碳技術，將熱焦炭淬火後產生的顯熱回收來產製電力或蒸汽，並同時降低焦碳濕式淬火所造成之汙染問題以及增加焦碳之性能。此系統循環風進入CDQ，在冷卻焦炭的過程中，帶走焦炭中部分的C，其與補入空氣中的氧燃燒，本研究的主要目的在於讓燒損的C完全燃燒，降低能源的浪費。
本研究利用數據建模的方式控制CDQ系統以提升蒸氣產量。首先，證實蒸氣產量與鍋爐進氣溫度間有高度相關性，接著以非線性變數選取方法分別建立鍋爐進氣溫度及循環氣體中一氧化碳成分之模型，以此達到模型預測控制(Model Predictive Control , MPC)，用於調整補空氣量以提升至最大蒸氣產量。研究結果，與原工廠操作比較，MPC操作確實能有效提升蒸氣產量達7%。本研究所提出的方法，藉由大量的操作數據建立預測模式，無需修改現有的系統，也不需要額外的設備投資，以投資回收的角度來看，本研究方法對於製程的改善相當顯著。

目錄
摘要 I
目錄 II
圖目錄 IV
表目錄 V
第一章 緒論 1
1.1 前言 1
1.2 文獻回顧 2
1.3 研究動機與目的 7
第二章 研究方法 8
2.1 模型預測控制 8
2.2 LASSO-ANN 非線性變數選取與建模 10
2.2.1 LASSO變數選取 10
2.2.2 LASSO-ANN演算法 12
第三章 結果與討論 15
3.1 CDQ系統流程簡介 15
3.2 CDQ系統狀態分析 17
3.2.1蒸氣產量與鍋爐進氣溫度間相關性 17
3.2.2 CDQ系統之穩定與不穩定狀態 21
3.3 TCGB(K+1)模型建立 22
3.4 CCO(K+1)模型建立 26
3.5 MPC數學模型 28
3.6 結果與討論 29
第四章 結論 34
參考文獻 35

[1] P. H. Lin, P. H. Wang, and A. Huang, "Exergy analysis of a coke dry quenching system," China Steel Technical Report, vol. 22, pp. 63-67, 2009.
[2] G. Bisio and G. Rubatto, "Energy saving and some environment improvements in coke-oven plants," Energy, vol. 25, pp. 247-265, 2000.
[3] M. R. Errera and L. F. Milanez, "Thermodynamic analysis of a coke dry quenching unit," Energy conversion and management, vol. 41, pp. 109-127, 2000.
[4] D. Wang, T. Yang, Z. Wen, J.-X. Feng, N. Kong, Q. Wang, et al., "A Mathematical Model for Optimized Operation and Control in a CDQ-Boiler System," International Journal of Minerals, Metallurgy and Materials, vol. 12, pp. 390-393, 2005.
[5] J. B. Sheng, "Analysis and optimization of operating process of dry coke quenching," WISCO Technology, vol. 46, pp. 1-3, 2008.
[6] D. Jiang, Meng, Z., Li, X., Zhang, N., "Calibration of burning loss rate and research about process parameters optimization of coke dry quenching " China Resources Comprehensive Utilization, vol. 30, pp. 41-43, 2012.
[7] P. H. Lin, Wang, P. H. and Huang, A. T., "Exergy analysis of a coke dry quenching system," China Steel Technical Report, pp. 63-67, 2009.
[8] H. Liu, X. Zhang, L. Xu, and M. Wang, "Mathematical model for fluid flow and heat transfer in the cooling shaft of Coke Dry Quenching unit," Journal of Thermal Science, vol. 11, pp. 65-73, 2002.
[9] Y. Feng, X. Zhang, Q. Yu, Z. Shi, Z. Liu, H. Zhang, et al., "Experimental and numerical investigations of coke descending behavior in a coke dry quenching cooling shaft," Applied Thermal Engineering, vol. 28, pp. 1485-1490, 2008.
[10] L. Y. Sun, Y. D. Liu, C. Zhai, and H. Zhou, "Process simulation of an integrated coke dry quenching combined gasification," Petroleum & Coal, vol. 54, pp. 34-41, 2012.
[11] E. F. Camacho, C. Bordons, E. F. Camacho, and C. Bordons, Model predictive control vol. 2: Springer London,, 2004.
[12] D. Q. Mayne, J. B. Rawlings, C. V. Rao, and P. O. Scokaert, "Constrained model predictive control: Stability and optimality," Automatica, vol. 36, pp. 789-814, 2000.
[13] R. Findeisen and F. Allgöwer, "An introduction to nonlinear model predictive control," in 21st Benelux Meeting on Systems and Control,, 2002.
[14] T. G. Hovgaard, L. F. Larsen, K. Edlund, and J. B. Jørgensen, "Model predictive control technologies for efficient and flexible power consumption in refrigeration systems," Energy, vol. 44, pp. 105-116, 2012.
[15] M. Lazar and O. Pastravanu, "A neural predictive controller for non-linear systems," Mathematics and Computers in Simulation, vol. 60, pp. 315-324, 2002.
[16] P. Kittisupakorn, P. Thitiyasook, M. Hussain, and W. Daosud, "Neural network based model predictive control for a steel pickling process," Journal of Process Control, vol. 19, pp. 579-590, 2009.
[17] S. Hajimolana, S. Tonekabonimoghadam, M. Hussain, M. Chakrabarti, N. Jayakumar, and M. Hashim, "Thermal stress management of a solid oxide fuel cell using neural network predictive control," Energy, vol. 62, pp. 320-329, 2013.
[18] J. Zhang, Y. Zhou, R. Wang, J. Xu, and F. Fang, "Modeling and constrained multivariable predictive control for ORC (Organic Rankine Cycle) based waste heat energy conversion systems," Energy, 2014.
[19] V. Onnia and J. Saarinen, "Feature selection method using neural network Proceedings," presented at the 2001 International Conference on Image Processing, 2001.
[20] E. Romero and J. M. Sopena, "Performing feature selection with multilayer perceptrons," IEEE Transactions on Neural Networks, vol. 19, pp. 431-441, 2008.
[21] R. J. May, H. R. Maier, G. C. Dandy, and T. M. K. Fernando, "Non-linear variable selection for artificial neural networks using partial mutual information," Environmental Modelling & Software, vol. 23, pp. 1312-1326, 2008.
[22] F. A. Souza, R. Araújo, T. Matias, and J. Mendes, "A multilayer-perceptron based method for variable selection in soft sensor design," Journal of Process Control, vol. 23, pp. 1371-1378, 2013.
[23] K. Sun, J. Liu, J. L. Kang, S. S. Jang, D. S. H. Wong, and D. S. Chen, "Development of a variable selection method for soft sensor using artificial neural network and nonnegative garrote," Journal of Process Control, In press.
[24] R. Tibshirani, "Regression shrinkage and selection via the lasso," Journal of the Royal Statistical Society. Series B (Methodological), pp. 267-288, 1996.
[25] B. Efron, T. Hastie, I. Johnstone, and R. Tibshirani, "Least angle regression," The Annals of statistics, vol. 32, pp. 407-499, 2004.
[26] 李政諭, "應用模型預測控制器於機車引擎空燃比控制," 車輛工程系, 國立台北科技大學, 2010.
[27] 盧俊男, "模型預測控制設計及於雙線性伺服系統之應用," 機械工程學系, 國立成功大學, 2008.
[28] S. Haykin, Neural networks: a comprehensive foundation: Prentice Hall PTR,, 1994.