Research Papers

Fault Diagnosis of Solid Oxide Fuel Cell Based on a Supervised Self-Organization Map Model

[+] Author and Article Information
XiaoJuan Wu

School of Automation,
University of Electronic Science and Technology of China,
Chengdu 610054, China
e-mail: xj2_wu@ hotmail.com

Hongtan Liu

Clean Energy Research Institute,
College of Engineering,
University of Miami,
Coral Gables, FL 33146

1Corresponding author.

Contributed by the Advanced Energy Systems Division of ASME for publication in the JOURNAL OF FUEL CELL SCIENCE AND TECHNOLOGY. Manuscript received November 26, 2013; final manuscript received October 31, 2014; published online January 28, 2015. Assoc. Editor: Ellen Ivers-Tiffée.

J. Fuel Cell Sci. Technol 12(3), 031001 (Jun 01, 2015) (8 pages) Paper No: FC-13-1112; doi: 10.1115/1.4029070 History: Received November 26, 2013; Revised October 31, 2014; Online January 28, 2015

Too high stack temperature and insufficient reactant gas flow may lead to severe and irreversible damages in a real solid oxide fuel cell (SOFC) power system. Thus, fault monitoring and diagnosis technology is indispensable to improve the SOFC system reliability. A supervised self-organization map (SOM) model is proposed to diagnose the faults of the SOFC system in this paper. Using the supervised SOM model, the multidimensional testing data of the SOFC is mapped into a two-dimensional map, and the different region in the out map is represented for one fault mode. The method is evaluated using the data obtained from an SOFC mathematical model, and the results show that the supervised SOM analysis contributes on a very efficient way to the faults diagnosis of the SOFC system.

Copyright © 2015 by ASME
Your Session has timed out. Please sign back in to continue.


National Energy Technology Laboratory, 2009, “ Hydrogen Posture Plan,” U.S. Department of Energy, Washington, DC, accessed Aug. 15, 2011, http://www.netl.doe.gov/technologies/hydrogen_clean_fuels
Astroma, K., Fontell, E., and Virtanen, S., 2007, “Reliability Analysis and Initial Requirements for FC Systems and Stacks,” J. Power Sources, 171(1), pp. 46–54. [CrossRef]
Yousfi Steiner, N., Hissel, D., Moçotéguy, P., Candusso, D., Marra, D., Pianese, C., and Sorrentino, M., 2012, “Application of Fault Tree Analysis to Fuel Cell Diagnosis,” Fuel Cells, 12(2), pp. 302–309. [CrossRef]
Sun, Y. L., Ghantasala, S., and El-Farra, N. H., 2010, “Monitoring and Fault-Tolerant Control of Distributed Power Generation: Application to Solid Oxide Fuel Cells,” American Control Conference (ACC), Baltimore, MD, June 30–July 2, pp. 448–453. [CrossRef]
Huang, Q. A., Hui, R., Wang, B., and Zhang, J., 2007, “A Review of AC Impedance Modeling and Validation in SOFC Diagnosis,” Electrochim. Acta, 52(28), pp. 8144–8164. [CrossRef]
Comminges, C., Fua, Q. X., Zahid, M., Steiner, N. Y., and Bucheli, O., 2012, “Monitoring the Degradation of a Solid Oxide Fuel Cell Stack During 10,000 h Via Electrochemical Impedance Spectroscopy,” Electrochim. Acta, 59, pp. 367–375. [CrossRef]
Sorrentino, M., and Pianese, C., 2009, “Grey-Box Modeling of SOFC Unit for Design, Control and Diagnostics Applications,” European Fuel Cell Forum, Lucerne, Switzerland, June 29–July 2, Paper No. 12.
Murshed, AKM M., Huang, B., and Nandakumar, K., 2011, “Monitoring of Solid Oxide Fuel Cell Systems,” Asia-Pac. J. Chem. Eng., 6(2), pp. 204–219. [CrossRef]
Papadimitriou, S., Mavroudi, S., VladutuIschemia, L., and Bezerianos, A., 2001, “Detection With a Self-Organizing Map Supplemented by Supervised Learning,” IEEE Trans. Neural Networks, 12(3), pp. 503–514. [CrossRef]
Pakkanen, J., and Iivarinen, J., 2004, “A Novel Self-Organizing Neural Network for Defect Image Classification,” IEEE International Joint Conference on Neural Networks (IJCNN 2004), Budapest, Hungary, July 25–29, pp. 2553–2556. [CrossRef]
Jiang, D. B., Yang, Y. H., and Xia, M., 2009, “Research on Intrusion Detection Based on an Improved SOM Neural Network,” Fifth International Conference on Information Assurance and Security (IAS ’09), Xi'an, China, Aug. 18–20, pp. 400–403. [CrossRef]
Wu, X. J., Huang, Q., and Zhu, X. J., 2011, “Thermal Modeling of a Solid Oxide Fuel Cell and Micro Gas Turbine Hybrid Power System Based on Modified LS-SVM,” Int. J. Hydrogen Energy, 36(1),pp. 885–892. [CrossRef]
Ataer, O. E., Ileri, A., and Gogus, Y., 1995, “Transient Behavior of Finned-Tube Cross-Flow Heat Exchangers,” Int. J. Refrig., 18(3), pp. 153–160. [CrossRef]
Sorrentino, M., and Pianese, C., 2011, “Model-Based Development of Low-Level Control Strategies for Transient Operation of Solid Oxide Fuel Cell Systems,” J. Power Sources, 196(21), pp. 9036–9045. [CrossRef]
Lefebvre, G., Laurent, C., Ros, J., and Garcia, C., 2006, “Supervised Image Classification by SOM Activity Map Comparison,” 18th International Conference on Pattern Recognition (ICPR 2006), Hong Kong, China, Aug. 20–24, Vol. 2, pp. 728–731. [CrossRef]


Grahic Jump Location
Fig. 1

Structure diagram of SOFC system

Grahic Jump Location
Fig. 4

Evolution of variables by fault in the temperature controller: (a) SOFC stack voltage, (b) SOFC stack power, (c) SOFC stack temperature, and (d) compressor power

Grahic Jump Location
Fig. 3

Temperature control architecture

Grahic Jump Location
Fig. 2

SOFC system model developed in matlab

Grahic Jump Location
Fig. 5

Evolution of variables by air leakage fault: (a) SOFC stack voltage, (b) SOFC stack power, (c) SOFC stack temperature, and (d) compressor power

Grahic Jump Location
Fig. 6

Evolution of variables by two faults: (a) SOFC stack voltage, (b) SOFC stack power, (c) SOFC stack temperature, and (d) compressor power

Grahic Jump Location
Fig. 8

Classified results of training samples

Grahic Jump Location
Fig. 7

Supervised SOM topology

Grahic Jump Location
Fig. 9

Classified results of testing samples



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