Research Paper

Performance Optimization and Selection of Operating Parameters for a Solid Oxide Fuel Cell Stack

[+] Author and Article Information
Shih-Bin Wang

The Graduate Institute of Design Science,
Tatung University,
No. 40, Sec. 3, Zhongshan North Road,
Taipei 104, Taiwan;
Lee Ming Institute of Technology,
2-2, Lee-Juan Road, Tai-Shan,
New Taipei City 243, Taiwan
e-mail: wsb@mail.lit.edu.tw

Chih-Fu Wu

The Graduate Institute of Design Science,
Tatung University,
No. 40, Sec. 3, Zhongshan North Road,
Taipei 104, Taiwan

Ping Yuan

Lee Ming Institute of Technology,
2-2, Lee-Juan Road, Tai-Shan,
New Taipei City 243, Taiwan

Contributed by the Advanced Energy Systems Division of ASME for publication in the Journal of Fuel Cell Science and Technology. Manuscript received January 12, 2013; final manuscript received June 12, 2013; published online August 20, 2013. Assoc. Editor: Dr Masashi Mori.

J. Fuel Cell Sci. Technol 10(5), 051005 (Aug 20, 2013) (11 pages) Paper No: FC-13-1003; doi: 10.1115/1.4024966 History: Received January 12, 2013; Revised June 12, 2013

In this study, a model of current densities for a ten-cell solid oxide fuel cell (SOFC) stack is learned and developed due to the utilization of an improved backpropagation neural network (BPNN). To build the learning data of the BPNN, the operating parameters are suitably arranged by the Taguchi orthogonal array, which totals seven factors with five levels, respectively, that act as the inputs of BPNN. Also, the average current densities for the ten-cell SOFC stack achieved by the numerical method act as the outputs of the BPNN. The effectiveness of the developed BPNN mathematical algorithm to predict performance of the SOFC stack is proved by the learning errors smaller than 0.11% and the predicting errors less than 0.52%. Then, the calculating algorithms of the BPNN are adopted to proceed with the optimization based on the electrical performance of the sum of the average current densities for the ten-cell SOFC stack. Thus, the best and the worst performances are found to be Fmax = 57795.622 Am−2 and Fmin = 33939.362 Am−2, respectively. It is also the operating window of the performance for the SOFC stack developed by the improved BPNN. Furthermore, an inverse predicting model of the SOFC stack is developed by the calculating algorithms of the BPNN. This model is proved to effectively predict the operating parameters to achieve a desired performance output of the SOFC stack. Combination of these calculating algorithms developed by the improved BPNN gives the possibility to complete dynamic control of the operating parameters, such as the mole fraction of species and mole flow rate in the inlet, which are considered to be changeable.

Copyright © 2013 by ASME
Your Session has timed out. Please sign back in to continue.


Yakabe, H., Ogiwara, T., Hishinuma, M., and Yasuda, I., 2001, “3-D Model Calculation for Planar SOFC,” J. Power Sources, 102, pp. 144–154. [CrossRef]
Recknagle, K. P., Williford, R. E., Chick, L. A., Rector, D. R., and Khaleel, M. A., 2003, “Three-Dimensional Thermo-Fluid Electrochemical Modeling of Planar SOFC Stacks,” J. Power Sources, 113, pp. 109–114. [CrossRef]
Lu, Y., Schaefer, L., and Li, P., 2005, “Numerical Simulation of Heat Transfer and Fluid Flow of a Flat-Tube High Power Density Solid Oxide Fuel Cell,” ASME J. Fuel Cell Sci. Technol., 2, pp. 65–69. [CrossRef]
Huang, J. J., ChenC. K., and LaiD. Y., 2005, “Computational Analysis of Species Transport and Electrochemical Characteristics of a MOLB-Type SOFC,” J. Power Sources, 140, pp. 235–242. [CrossRef]
Ji, Y., Yuana, K., Chunga, J. N., and Chen, Y. C., 2006, “Effects of Transport Scale on Heat/Mass Transfer and Performance Optimization for Solid Oxide Fuel Cells,” J. Power Sources, 161, pp. 380–391. [CrossRef]
Janardhanan, V. M., Heuveline, V., and Deutschmann, O., 2007, “Performance Analysis of a SOFC Under Direct Internal Reforming Conditions,” J. Power Sources, 172, pp. 296–307. [CrossRef]
Haberman, B. A., and Young, J. B., 2008, “A Detailed Three-Dimensional Simulation of an IP-SOFC Stack,” ASME J. Fuel Cell Sci. Technol., 5, pp. 1–12. [CrossRef]
Boersma, R. J., and Sammes, N. M., 1997, “Distribution of Gas Flow in Internally Manifolded Solid Oxide Fuel-Cell Stacks,” J. Power Sources, 66, pp. 41–45. [CrossRef]
Okada, T., Matsumoto, S., Matsumura, M., Miyazaki, M., and Umeda, M., 2006, “Gas Distribution in Molten-Carbonate Fuel Cells,” J. Power Sources, 162, pp. 1029–1035. [CrossRef]
Yuan, P., and Liu, S. F., 2007, “Numerical Analysis of Temperature and Current Density Distribution of a Planar Solid Oxide Fuel Cell Unit With Non-Uniform Inlet Flow,” Numer. Heat Transfer, Part A, 51, pp. 941–957. [CrossRef]
Yuan, P., 2008, “Effect of Inlet Flow Maldistribution in the Stacking Direction on the Performance of a Solid Oxide Fuel Cell Stack,” J. Power Sources, 185, pp. 381–391. [CrossRef]
Liu, S. F., Chiang, M. S., Wang, S. B., and Yuan, P., 2011, “Electrical and Thermal Performance of a Solid Oxide Fuel Cell Unit With Non-Uniform Inlet Flow and High Fuel Utilization,” ASME J. Fuel Cell Sci. Technol., 8, p. 031002. [CrossRef]
Arriagada, J., Olausson, P., and Selimovic, A., 2002, “Artificial Neural Network Simulator for SOFC Performance Prediction,” J. Power Sources, 112, pp. 54–60. [CrossRef]
Wu, X. J., Zhu, X. J., Cao, G. Y., and Tu, H. Y., 2007, “Modeling a SOFC Stack Based on GA-RBF Neural Networks Identification,” J. Power Sources, 167, pp. 145–150. [CrossRef]
Milewski, J., and Świrski, K., 2009, “Modelling the SOFC Behaviours by Artificial Neural Network,” Int. J. Hydrogen Energy, 34, pp. 5546–5553. [CrossRef]
Larminie, J., and Dicks, A., 2000, Fuel Cell Systems Explained, 1st ed., Wiley, New York, p. 53.
Maric, R., Ohara, S., Fukui, T., Yoshida, H., Nishimura, M., Inagaki, T., and Miura, K., 1999, “Solid Oxide Fuel Cells With Doped Lanthanum Gallate Electrolyte and LaSrCoO3 Cathode, and Ni-Samaria-Doped Ceria Cermet Anode,” J. Electrochem. Soc., 146, pp. 2006–2010. [CrossRef]
Hines, A. L., and Maddox, R. N., 1985, Mass Transfer Fundamentals and Applications, Prentice-Hall, Englewood Cliffs, NJ, pp. 17–59.
Wang, S. B., and Wu, C. F., 2006, “Selections of Working Conditions for Creep Feed Grinding. Part (III): Avoidance of the Work Piece Burning by Using Improved BP Neural Network,” Int. J. Adv. Manuf. Technol., 28, pp. 31–37. [CrossRef]
Rangwala, S., and Dornfeld, D., 1989, “Learning and Optimization of Machining Operations Using Computing Abilities of Neural Networks,” IEEE Trans. Syst. Man Cybern., 19(2), pp. 299–314. [CrossRef]
Taguchi, G., 1991, Introduction to Quality Engineering, Asian Productivity Organization, UNIPUB, White Plains, NY.


Grahic Jump Location
Fig. 1

Schematic diagram of a unit solid oxide fuel cell stack with crossflow configuration [11]

Grahic Jump Location
Fig. 2

Whole SOFC stack with inlet flow distributions

Grahic Jump Location
Fig. 3

Schematic diagram of a neuron model

Grahic Jump Location
Fig. 4

The response graphs of all factors and their levels

Grahic Jump Location
Fig. 5

The converging process of optimization

Grahic Jump Location
Fig. 6

The converging process of inverse prediction of operating parameters for desired performances of the SOFC stack



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In