Neural network hybrid model of a direct internal reforming solid oxide fuel cell

Abstract A mathematical model is an important tool for analysis and design of fuel cell stacks and systems. In general, the complete description of fuel cells requires an electrochemical model to predict their electrical characteristics, i.e., cell voltage and current density. However, obtaining the electrochemical model is quite a difficult and complicated task as it involves various operational, structural and electrochemical reaction parameters. In this study, a neural network model was first proposed to predict the electrochemical characteristics of solid oxide fuel cell (SOFC). Various NN structures were trained based on the back-propagation feed-forward approach. The results showed that the NN with optimal structure reliably provides a good estimation of fuel cell electrical characteristics. Then, a neural network hybrid model of a direct internal reforming SOFC, combining mass conservation equations with the NN model, was developed to determine the distributions of gaseous components in fuel and air channels of SOFC as well as the performance of the SOFC in terms of power density and fuel cell efficiency. The effects of various key parameters, e.g., temperature, pressure, steam to carbon ratio, degree of pre-reforming, and inlet fuel flow rate on the SOFC performance under steady-state and isothermal conditions were also investigated. A combination of the first principle model and NN presents a significant advantage of predicting the SOFC performance with accuracy and less computational time.

[1]  Wei-Kang Yuan,et al.  A hybrid neural network-first principles model for fixed-bed reactor , 1999 .

[2]  Jaime Arriagada,et al.  Artificial neural network simulator for SOFC performance prediction , 2002 .

[3]  S. Chan,et al.  A complete polarization model of a solid oxide fuel cell and its sensitivity to the change of cell component thickness , 2001 .

[4]  N. Sammes,et al.  Dynamic modeling of single tubular SOFC combining heat/mass transfer and electrochemical reaction effects , 2005 .

[5]  Phillip N. Hutton,et al.  A cell-level model for a solid oxide fuel cell operated with syngas from a gasification process , 2005 .

[6]  Yoshio Matsuzaki,et al.  Evaluation and modeling of performance of anode-supported solid oxide fuel cell , 2000 .

[7]  L. Kershenbaum,et al.  Modelling of an indirect internal reforming solid oxide fuel cell , 2002 .

[8]  M. De Paepe,et al.  Performance of combined internally reformed intermediate/ high temperature SOFC cycle compared to internally reformed two-staged intermediate temperature SOFC cycle , 2008 .

[9]  Luke E. K. Achenie,et al.  A hybrid neural network model for PEM fuel cells , 2005 .

[10]  Yaohui Zhang,et al.  Anode-supported solid oxide fuel cell based on dense electrolyte membrane fabricated by filter-coating , 2006 .

[11]  Amornchai Arpornwichanop,et al.  Neural network inverse model-based controller for the control of a steel pickling process , 2005, Comput. Chem. Eng..

[12]  Won-Yong Lee,et al.  Empirical modeling of polymer electrolyte membrane fuel cell performance using artificial neural networks , 2004 .

[13]  B. Haberman,et al.  Three-dimensional simulation of chemically reacting gas flows in the porous support structure of an integrated-planar solid oxide fuel cell , 2004 .

[14]  S. Assabumrungrat,et al.  Performance evaluation of combined solid oxide fuel cells with different electrolytes , 2010 .

[15]  R. Peters,et al.  Internal reforming of methane in solid oxide fuel cell systems , 2002 .

[16]  Ali Elkamel,et al.  Hybrid artificial neural network—First principle model formulation for the unsteady state simulation and analysis of a packed bed reactor for CO2 hydrogenation to methanol , 2005 .

[17]  Vincenzo Antonucci,et al.  High power fuel cell simulator based on artificial neural network , 2010 .

[18]  Haralambos Sarimveis,et al.  Development of a novel computational tool for optimizing the operation of fuel cells systems: Application for phosphoric acid fuel cells , 2008 .

[19]  S. Kakaç,et al.  A review of numerical modeling of solid oxide fuel cells , 2007 .

[20]  Dexian Huang,et al.  Combining first principles with black-box techniques for reaction systems , 2000 .

[21]  Mohd Azlan Hussain,et al.  Hybrid neural network—prior knowledge model in temperature control of a semi-batch polymerization process , 2004 .

[22]  Amornchai Arpornwichanop,et al.  Performance of an anode-supported solid oxide fuel cell with direct-internal reforming of ethanol , 2009 .

[23]  Amir Abtahi,et al.  Neural network model for a commercial PEM fuel cell system , 2007 .

[24]  R. Kee,et al.  A general mathematical model for analyzing the performance of fuel-cell membrane-electrode assemblies , 2003 .

[25]  A. Virkar,et al.  Dependence of polarization in anode-supported solid oxide fuel cells on various cell parameters , 2005 .

[26]  D. Leung,et al.  Parametric study of solid oxide fuel cell performance , 2007 .

[27]  C. Adjiman,et al.  Anode-supported intermediate temperature direct internal reforming solid oxide fuel cell. I: model-based steady-state performance , 2004 .

[28]  Amornchai Arpornwichanop,et al.  Electrochemical study of a planar solid oxide fuel cell: Role of support structures , 2008 .

[29]  Jarosław Milewski,et al.  Modelling the SOFC behaviours by artificial neural network , 2009 .

[30]  M. Fowler,et al.  Performance comparison of Fick’s, dusty-gas and Stefan–Maxwell models to predict the concentration overpotential of a SOFC anode , 2003 .

[31]  S. Chan,et al.  Performance evaluation of anode-supported solid oxide fuel cells with thin film YSZ electrolyte , 2004 .

[32]  Xin-Jian Zhu,et al.  Short communication Modeling a SOFC stack based on GA-RBF neural networks identification , 2007 .

[33]  D. C. Psichogios,et al.  Direct and indirect model based control using artificial neural networks , 1991 .

[34]  E. Riensche,et al.  Methane/steam reforming kinetics for solid oxide fuel cells , 1994 .