近年來各發電廠為了因應碳排所造成溫室效應議題，開始使用較潔淨的甲烷原料取代以往的煤炭原料，由於煤炭高可靠且成本低廉的特性，使得煤炭仍為發電燃料供應的主要來源。為了使發電需求、發電成本與碳排之間取得平衡，本研究設計兩個分別以甲烷及煤碳為原料的發電系統，藉由倒傳遞類神經網路預測每月天然氣價格、煤碳價格及電力需求，並考慮系統動態及碳稅等相關因素以計算未來發電成本，針對兩個發電系統進行電力的配比計算。
本研究透過Aspen Custom Modeler(ACM)建立的固態氧化物燃料電池模型並以Aspen Plus的內建單元及模型模擬整合天然氣複循環燃料電池系統(NGFC)及整合煤氣化燃料電池發電系統(IGFC)，此兩個發電系統主要以固態氧化燃料電池(SOFC)以及汽渦輪系統(GT)作為主要發電方式，為了瞭解系統的特性及操作條件，使用靈敏度分析找出燃料處理程序(Fuel processor)、固態氧化燃料電池(SOFC)以及汽渦輪系統(GT)等主要架構的操作條件。
此外，為了預測天然氣價格、煤碳價格及電力需求，以MATLAB內建的工具箱進行分析，以偏最小二乘回歸(PLSR)及高斯過程回歸(GPR)等方法找出適合建模的影響因素，並以倒傳遞類神經網路模型(BP-NN)為主要模型進行預測。
為了進一步貼近實務的情況，將兩個發電系統進行動態模擬，基於庫存控制維持系統平衡，並考慮後燃器燃燒的安全考量設置交叉限制燃燒控制，並以此設計為後續品質控制設計的基礎，為了實現總發電量的彈性控制及進料量等限制，採用I串級模型預測控制器(MPC)進行控制，並以配比計算所得到結果作為控制設定點，在維持總電量需求的情況下達到設定點的需求。

In recent years, power plants start to utilize methane instead of coal due to lesser carbon emissions and in order to deal with global warming. At present, coal remains to be the most reliable source of energy for power plant because of cheaper cost. Power generation requirements, costs and carbon emissions are the three primary factors that needs to be analyzed for an optimum energy production. Therefore, the study will analyze two power systems using methane and coal as raw materials. The study will cover the prediction of the cost of natural gas, coal and energy demand using the Back Propagation Neural Network. Moreover, the study will include related factors such as system dynamics and carbon tax to calculate future power generation costs followed by the power dispatch calculations.
The study utilized the Aspen Custom Modeler® and Aspen Plus® model for the design of the two systems: natural gas fuel cell (NGFC) and integrated coal gasification fuel cell (IGFC). The partial least squares regression (PLSR) and Gaussian process regression (GPR) model was used to find the impact factors using the MATLAB® toolbox to predict the electricity demand, natural gas and coal prices. Moreover, this study discussed the dynamic simulation using the results of power dispatch as the setpoint of model predictive controls (MPC).
The forecasted results showed a reduction error on the cost of coal and methane and the energy demand of about 26 – 78% and it can improve the GPR by at least 3% error.

[1] "BP Statistical Review of World Energy June 2017," BP World Energy.
[2] "次世代火力発電に係る技術ロードマップを策定しました，經濟產業省，2016/6/30。."
[3] "次世代火力発電に係る技術ロードマップ，次世代火力発電の早期実現に向けた協議会，2016/6/30。."
[4] "次世代火力発電に係る技術ロードマップ技術参考資料集，次世代火力発電の早期実現に向けた協議会，2016/6/30。."
[5] J. Richardson and S. Paripatyadar, "Carbon dioxide reforming of methane with supported rhodium," Applied Catalysis, vol. 61, no. 1, pp. 293-309, 1990.
[6] C. Alie, L. Backham, E. Croiset, and P. L. Douglas, "Simulation of CO2 capture using MEA scrubbing: a flowsheet decomposition method," Energy Conversion and Management, vol. 46, no. 3, pp. 475-487, 2005/02/01/ 2005.
[7] W. L. Luyben, Chemical reactor design and control. John Wiley & Sons, 2007.
[8] P. J. Robinson and W. L. Luyben, "Simple dynamic gasifier model that runs in Aspen Dynamics," Industrial & engineering chemistry research, vol. 47, no. 20, pp. 7784-7792, 2008.
[9] P. J. Robinson and W. L. Luyben, "Integrated Gasification Combined Cycle Dynamic Model: H2S Absorption/Stripping, Water−Gas Shift Reactors, and CO2 Absorption/Stripping," Industrial & Engineering Chemistry Research, vol. 49, no. 10, pp. 4766-4781, 2010/05/19 2010.
[10] B. Thorud, "Dynamic modelling and characterisation of a solid oxide fuel cell integrated in a gas turbine cycle," 2005.
[11] S. C. Singhal and K. Kendall, High-temperature solid oxide fuel cells: fundamentals, design and applications. Elsevier, 2003.
[12] F. Calise, A. Palombo, and L. Vanoli, "Design and partial load exergy analysis of hybrid SOFC–GT power plant," Journal of power sources, vol. 158, no. 1, pp. 225-244, 2006.
[13] S. Campanari and P. Iora, "Definition and sensitivity analysis of a finite volume SOFC model for a tubular cell geometry," Journal of Power Sources, vol. 132, no. 1, pp. 113-126, 2004/05/20/ 2004.
[14] F. Jurado, "Predictive control of solid oxide fuel cells using fuzzy Hammerstein models," Journal of Power Sources, vol. 158, no. 1, pp. 245-253, 2006.
[15] X. Zhang, J. Li, G. Li, and Z. Feng, "Numerical study on the thermal characteristics in a tubular solid oxide fuel cell with indirect internal reformer," International Journal of Thermal Sciences, vol. 48, no. 4, p. 805, 2009.
[16] N. Chatrattanawet, S. Skogestad, and A. Arpornwichanop, "Control structure design and dynamic modeling for a solid oxide fuel cell with direct internal reforming of methane," Chemical Engineering Research and Design, vol. 98, pp. 202-211, 2015.
[17] R. Kandepu, L. Imsland, B. A. Foss, C. Stiller, B. Thorud, and O. Bolland, "Modeling and control of a SOFC-GT-based autonomous power system," Energy, vol. 32, no. 4, pp. 406-417, 2007.
[18] J. M. Smith, "Introduction to chemical engineering thermodynamics," ed: ACS Publications, 1950.
[19] W. S. McCulloch and W. Pitts, "A logical calculus of the ideas immanent in nervous activity," The bulletin of mathematical biophysics, vol. 5, no. 4, pp. 115-133, 1943.
[20] J. J. Hopfield, "Neural networks and physical systems with emergent collective computational abilities," Proceedings of the national academy of sciences, vol. 79, no. 8, pp. 2554-2558, 1982.
[21] 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," 化學工程學研究所, 臺灣大學, 2007年, 2007.
[22] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning representations by back-propagating errors," nature, vol. 323, no. 6088, p. 533, 1986.
[23] M. C. Lee, S. B. Seo, J. H. Chung, S. M. Kim, Y. J. Joo, and D. H. Ahn, "Gas turbine combustion performance test of hydrogen and carbon monoxide synthetic gas," Fuel, vol. 89, no. 7, pp. 1485-1491, 2010.
[24] M. Granovskii, I. Dincer, and M. A. Rosen, "Performance comparison of two combined SOFC–gas turbine systems," Journal of Power Sources, vol. 165, no. 1, pp. 307-314, 2007.
[25] T. Benjamin, "Energy Efficiency in Pump Specification," World Pumps, vol. 2001, no. 415, pp. 26-33, 2001/04/01/ 2001.
[26] S. H. Chan, H. K. Ho, and Y. Tian, "Modelling of simple hybrid solid oxide fuel cell and gas turbine power plant," Journal of Power Sources, vol. 109, no. 1, pp. 111-120, 2002/06/15/ 2002.
[27] W. L. Luyben, B. D. Tyréus, and M. L. Luyben, Plantwide process control. McGraw-Hill New York, 1998.
[28] N. M. Konda, G. Rangaiah, and P. Krishnaswamy, "A simple and effective procedure for control degrees of freedom," Chemical Engineering Science, vol. 61, no. 4, pp. 1184-1194, 2006.
[29] W. L. Luyben, Distillation design and control using Aspen simulation. John Wiley & Sons, 2013.
[30] "IWA-2012-International-Statistics-for-Water-Services," International Water Association.
[31] "carbon tax 2017," https://www.carbontax.org/states/.
[32] "Electricity End Use," U.S. Energy Information Administration March 2018 Monthly Energy Review.
[33] K. Bennaceur, D. Gielen, T. Kerr, and C. Tam, CO2 capture and storage: a key carbon abatement option. OECD, 2008.
[34] R. J. Braun, S. Kameswaran, J. Yamanis, and E. Sun, "Highly Efficient IGFC Hybrid Power Systems Employing Bottoming Organic Rankine Cycles With Optional Carbon Capture," Journal of Engineering for Gas Turbines and Power, vol. 134, no. 2, pp. 021801-021801-15, 2011.
[35] M. Gazzani, E. Macchi, and G. Manzolini, "CAESAR: SEWGS integration into an IGCC plant," Energy Procedia, vol. 4, pp. 1096-1103, 2011.