Nonlinear Identification of a PEM Fuel Cell Humidifier Using Wavelet Networks

  • Xian-Rui Deng
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3973)


Humidification is a key factor influencing the performance of a Proton Exchange Membrane (PEM) Fuel Cell system. It is important to obtain an accurate temperature model of the humidifier to achieve the optimal humidity by means of some control strategy. Analysis shows that humidification process is nonlinear. To avoid the curse-of-dimensionality problem, a class of wavelet networks proposed by Billings was employed for the identification in this work. An efficient model term selection approach was applied to solve the high dimensional problem. The model was identified based on the experimental data acquired from our test bench. The one-step-ahead predictions and the five-step-ahead predictions were compared with the real measurements respectively. It shows that the identified model can effectively describe the real system.


Fuel Cell Multivariate Adaptive Regression Spline Fuel Cell System Polymer Electrolyte Membrane Fuel Cell Wavelet Network 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Farooque, M., Maru, H.C.: Fuel Cells-the Clean and Efficient Power Generators. In: Proceedings of the IEEE, vol. 89, pp. 1819–1829 (2001)Google Scholar
  2. 2.
    Chen, D.-M., Peng, H.: Modeling and Simulation of a PEM Fuel Cell Humidification System. In: Proceedings of 2004 American Control Conference, Boston, Massachusetts, vol. 1, pp. 822–827 (2004)Google Scholar
  3. 3.
    Ceraolo, M., Miuli, C., Pozio, A.: Modelling Static and Dynamic Behavior of Proton Exchange Membrane Fuel Cells on the Basis of Electro-chemical Description. J. Power Sources 113, 131–144 (2003)CrossRefGoogle Scholar
  4. 4.
    Janssen, G.J.M., Overvelde, M.L.J.: Water Transport in the Proton-Exchange-Membrane Fuel Cell: Measurements of the Effective Drag Coefficient. J. Power Sources 101, 117–125 (2001)CrossRefGoogle Scholar
  5. 5.
    Nguyen, T.V., White, R.E.: A Water and Heat Management Model for Proton-Exchange-Membrane Fuel Cells. J. Electrochem. Soc. 140, 2178–2186 (1993)CrossRefGoogle Scholar
  6. 6.
    Chen, D.-M., Peng, H.: Analysis of Non-Minimum Phase Behavior of PEM Fuel Cell Membrane Humidification Systems. In: Proceedings of 2005 American Control Conference, vol. 6, pp. 3853–3858 (2005)Google Scholar
  7. 7.
    Sridhar, P., Perumal, R., Rajalakshmi, N., Raja, M., Dhathathreyan, K.S.: Humidification Studies on Polymer Electrolyte Membrane Fuel Cell. J. Power Sources 101, 72–78 (2001)CrossRefGoogle Scholar
  8. 8.
    Billings, S.A., Wei, H.-L.: A New Class of Wavelet Networks for Nonlinear System Identification. IEEE Trans. Neural Netw. 16, 862–874 (2005)CrossRefGoogle Scholar
  9. 9.
    Zhang, Q.H., Benveniste, A.: Wavelet Networks. IEEE Trans. Neural Netw. 3, 889–898 (1992)CrossRefGoogle Scholar
  10. 10.
    Friedman, J.H.: Multivariate Adaptive Regression Splines. Ann. Statist. 19, 1–67 (1991)MATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    Wei, H.-L., Billings, S.A., Liu, J.: Term and Variable Selection for Nonlinear System Identification. Int. J. Control 77, 86–110 (2004)MATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Billings, S.A., Chen, S., Korenberg, M.J.: Identification of MIMO Nonlinear Systems Using a Forward Regression Orthogonal Estimator. Int. J. Control. 49, 2157–2189 (1989)MATHMathSciNetGoogle Scholar
  13. 13.
    Chen, S., Billings, S.A., Luo, W.: Orthogonal Least Squares Methods and Their Application to Nonlinear System Identification. Int. J. Control 50, 1873–1896 (1989)MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Xian-Rui Deng
    • 1
    • 2
  1. 1.Laboratory of Complex Systems and Intelligence ScienceInstitute of Automation Chinese Academy of SciencesBeijingChina
  2. 2.Computer DepartmentTangshan Teacher’s CollegeTangshanChina

Personalised recommendations