Modelling Architecture Parameters Of A Solid Oxide Fuel Cell Using A Hybrid-Artificial Neural Network

Łukasz Śladewski; Jaroslaw Milewski; Konrad Swirski; Aliaksandr Martsinchyk

doi:10.29284/g6nnch10

Authors

Łukasz Śladewski Warsaw University of Technology, Faculty of Power and Aeronautical Engineering, Institute of Heat Engineering, 21/25 Nowowiejska Street, 00-665 Warsaw, Poland
Jaroslaw Milewski Warsaw University of Technology, Faculty of Power and Aeronautical Engineering, Institute of Heat Engineering, 21/25 Nowowiejska Street, 00-665 Warsaw, Poland
Konrad Swirski Warsaw University of Technology, Faculty of Power and Aeronautical Engineering, Institute of Heat Engineering, 21/25 Nowowiejska Street, 00-665 Warsaw, Poland
Aliaksandr Martsinchyk Warsaw University of Technology, Faculty of Power and Aeronautical Engineering, Institute of Heat Engineering, 21/25 Nowowiejska Street, 00-665 Warsaw, Poland

DOI:

https://doi.org/10.29284/g6nnch10

Keywords:

Solid Oxide Fuel Cell; Hybrid Model; Artificial Neural Network; Architecture Parameters.

Abstract

An Artificial Neural Network (ANN) can predict and be applied to simulate an object’s behavior with no algorithmic solution merely by utilizing available experimental data. The error back-propagation algorithm was used for an ANN training procedure. There are SOFC features that cannot be expressed in numerical form or where numerical expression is difficult to obtain, i.e. electrolyte type, anode type, cathode type etc. In those situations, a hybrid model can be applied. The hybrid model (H-ANN) consists of the ANN model and mathematical expressions. The H-ANN can predict cell voltage with knowledge of minimum physical factors.

References

[1] T.F. Andrade and R. Muccillo. Effect of zinc oxide and boron oxide addition on the properties of yttrium-doped barium zirconate [efeito da adi¸c˜ao de ´oxido de zinco e de ´oxido de boro nas propriedades do zirconato de b´ario dopado com ´ıtrio]. Ceramica, 57(342):244–253, 2011.

[2] J. Arriagada, P. Olausson, and A. Selimovic. Artificial neural network simulator for SOFC performance prediction. Journal of Power Sources, 112(1):54–60, 2002.

[3] D.P. Bakalis and A.G. Stamatis. Incorporating available micro gas turbines and fuel cell: Matching considerations and performance evaluation. Applied Energy, 103:607–617, 2013.

[4] Ludger Blum, Robert Deja, Roland Peters, and Detlef Stolten. Comparison of efficiencies of low, mean and high temperature fuel cell systems. International Journal of Hydrogen Energy, 36(17):11056 – 11067, 2011.

[5] S. Bozorgmehri and M. Hamedi. Modeling and optimization of anode-supported solid oxide fuel cells on cell parameters via artificial neural network and genetic algorithm. Fuel Cells, 12(1):11–23, 2012.

[6] W. Budzianowski. Low-carbon power generation cycles: the feasibility of CO2 capture and opportunities for integration. Journal of Power Technologies, 91(1):6– 13, 2011.

[7] H. Cao, X. Li, Z. Deng, J. Jiang, J. Yang, J. Li, and Y. Qin. Dynamic modeling and experimental validation for the electrical coupling in a 5-cell solid oxide fuel cell stack in the perspective of thermal coupling. International Journal of Hydrogen Energy, 36(7):4409–4418, 2011.

[8] K. Chaichana, Y. Patcharavorachot, B. Chutichai, D. Saebea, S. Assabumrungrat, and A. Arpornwichanop. Neural network hybrid model of a direct internal reforming solid oxide fuel cell. International Journal of Hydrogen Energy, 37(3):2498–2508, 2012.

[9] K.L. Christman and M.K. Jensen. Solid oxide fuel cell performance with cross-flow roughness. Journal of Fuel Cell Science and Technology, 8(2):024501, 2011.

[10] G. De Lorenzo and P. Fragiacomo. Electrical and electrical-thermal power plants with molten carbonate fuel cell/gas turbine-integrated systems. International Journal of Energy Research, 36(2):153–165, 2012.

[11] G. De Lorenzo and P. Fragiacomo. A methodology for improving the performance of molten carbonate fuel cell/gas turbine hybrid systems. International Journal of Energy Research, 36(1):96–110, 2012.

[12] H. Demuth, M. Beale, and M. Hagan. Neural Network Toolbox 6 User’s Guide

[13] Matlab.

[14] G. Discepoli, G. Cinti, U. Desideri, D. Penchini, and S. Proietti. Carbon capture with molten carbonate fuel cells: Experimental tests and fuel cell performance assessment. International Journal of Greenhouse Gas Control, 9:372–384, 2012.

[15] E. Entchev and L. Yang. Application of adaptive neuro-fuzzy inference system techniques and artificial neural networks to predict solid oxide fuel cell performance in residential microgeneration installation. Journal of Power Sources, 170(1):122– 129, 2007.

[16] F.D. Foresee and M.T. Hagan. Gauss-newton approximation to bayesian regularization. In Proceedings of the 1997 International Joint Conference on Neural Networks, 1997.

[17] D. Grondin, J. Deseure, P. Ozil, J.-P. Chabriat, B. Grondin-Perez, and A. Brisse. Solid oxide electrolysis cell 3d simulation using artificial neural network for cathodic process description. Chemical Engineering Research and Design, 91(1):134–140, 2013.

[18] S.A. Hajimolana, M.A. Hussain, W.M.A.W. Daud, M. Soroush, and A. Shamiri. Mathematical modeling of solid oxide fuel cells: A review. Renewable and Sustainable Energy Reviews, 15(4):1893–1917, 2011.

[19] H.B. Huo, X.J. Zhu, and G.Y. Cao. Nonlinear modeling of a SOFC stack based on a least squares support vector machine. Journal of Power Sources, 162(2):1220–1225, 2006.

[20] H. Jeong, S. Cho, D. Kim, H. Pyun, D. Ha, C. Han, M. Kang, M. Jeong, and S. Lee. A heuristic method of variable selection based on principal component analysis and factor analysis for monitoring in a 300 kw mcfc power plant. International Journal of Hydrogen Energy, 37(15):11394–11400, 2012.

[21] Yi Jiang and Anil V. Virkar. Fuel composition and diluent effect on gas transport and performance of anode-supported sofcs. Journal of The Electrochemical Society, 150(7):A942–A951, 2003.

[22] F. Jurado. Power supply quality improvement with a SOFC plant by neuralnetwork-based control. Journal of Power Sources, 117(1-2):75–83, 2003.

[23] N. Kishor and S.R. Mohanty. Fuzzy modeling of fuel cell based on mutual information between variables. International Journal of Hydrogen Energy, 35(8):3620–3631, 2010.

[24] J. Kupecki and K. Badyda. SOFC-based micro-CHP system as an example of efficient power generation unit. Archives of Thermodynamics, 32(3):33–43, 2011.

[25] H. Marzooghi, M. Raoofat, M. Dehghani, and G.H. Elahi. Dynamic modeling of solid oxide fuel cell stack based on local linear model tree algorithm. International Journal of Hydrogen Energy, 37(5):4367–4376, 2012.

[26] Jarosl aw Milewski and Konrad Swirski. Modelling the SOFC behaviours by artificial´ neural network. International Journal of Hydrogen Energy, 34(13):5546–5553, 2009.

[27] Jarosl aw Milewski, Konrad Swirski, Massimo Santarelli, and Pierluigi Leone.´ Advanced Methods of Solid Oxide Fuel Cell Modeling. Springer-Verlag London Ltd., 1 edition, March 2011.

[28] R. Nomura, N. Iki, O. Kurata, M. Kawabata, A. Tsutsumi, E. Koda, and H. Furutani. System analysis of igfc with exergy recuperation utilizing low-grade coal. volume 4, pages 243–251, 2011.

[29] P. Pezzini, F. Caratozzolo, and A. Traverso. Real-time simulation of an experimental rig with pressurized sofc. volume 4, pages 113–121, 2011.

[30] P. Pianko-Oprych and Z. Jaworski. Numerical modelling of the micro-tubular solid oxide fuel cell stacks [przeglad metod modelowania numerycznego mikrorurowych stal otlenkowych stos´ow ognhw paliwowych]. Przemysl Chemiczny, 91(9):1813–1815, 2012.

[31] D. Sanchez, R. Chacartegui, J.M. Munoz de Escalona, A. Munoz, and T. Sanchez. Performance analysis of a MCFC & supercritical carbon dioxide hybrid cycle under part load operation. International Journal of Hydrogen Energy, 36(16):10327 – 10336, 2011.

[32] D. S´anchez, B. Monje, R. Chacartegui, and S. Campanari. Potential of molten carbonate fuel cells to enhance the performance of chp plants in sewage treatment facilities. International Journal of Hydrogen Energy, 38(1):394–405, 2013.

[33] A. Virkar and L. Wilson. Low-temperature, anode-supported high power density solid oxide fuel cells with nanostructured electrodes. Technical report, Department of Energy, USA, 2003.

[34] K. Wang, D. Hissel, M.C. Pera, N. Steiner, D. Marra, M. Sorrentino, C. Pianese, M. Monteverde, P. Cardone, and J. Saarinen. A review on solid oxide fuel cell models. International Journal of Hydrogen Energy, 36(12):7212–7228, 2011.

[35] J.-H. Wee. Molten carbonate fuel cell and gas turbine hybrid systems as distributed energy resources. Applied Energy, 88(12):4252–4263, 2011.

[36] X.J. Wu, X.J. Zhu, G.Y. Cao, and H.Y. Tu. Modeling a SOFC stack based on ga-rbf neural networks identification. Journal of Power Sources, 167(1):145–150, 2007.

[37] X.J. Wu, X.J. Zhu, G.Y. Cao, and H.Y. Tu. Nonlinear modelling of a SOFC stack by improved neural networks identification. Zhejiang University Press, 8:1505–1509, 2007.

[38] H. Zhang, G. Lin, and J. Chen. Performance analysis and multi-objective optimization of a new molten carbonate fuel cell system. International Journal of Hydrogen Energy, 36(6):4015–4021, 2011.

[39] Feng Zhao and A. Virkar. Dependence of polarization in anode-supported solid oxide fuel cells on various cell parameters. Journal of Power Sources, 141(1):79 – 95, 2005.