Nonlinear Modeling of the PEMFC Based On NNARX Approach

Polymer Electrolyte Membrane Fuel Cell (PEMFC) is such a time-vary nonlinear dynamic system. The traditional linear modeling approach is hard to estimate structure correctly of PEMFC system. From this reason, this paper presents a nonlinear modeling of the PEMFC using Neural Network Auto-regressive model with eXogenous inputs (NNARX) approach. The multilayer perception (MLP) network is applied to evaluate the structure of the NNARX model of PEMFC. The validity and accuracy of NNARX model are tested by one step ahead relating output voltage to input current from measured experimental of PEMFC. The results show that the obtained nonlinear NNARX model can efficiently approximate the dynamic mode of the PEMFC and model output and system measured output consistently.

Authors:

• Shan-Jen Cheng
• Te-Jen Chang
• Kuang-Hsiung Tan
• Shou-Ling Kuo

Keywords:

• PEMFC
• neural network
• nonlinear identification
• NNARX.

References:

[1] J. Jia, G. Wang, Y. T. Cham, Y. Wang, and M. Han, “Electrical
characteristic study of a hybrid PEMFC and ultracapacitor system,” IEEE
Trans. Ind. Electron., vol. 57, no. 6, pp. 1945–1953, Jun. 2010.
[2] K. Jin, X. Ruan, M. Yang, and M. Xu, “A hybrid fuel cell power system,”
IEEE Trans. Ind. Electron., vol. 56, no. 4, pp. 1212–1222, Apr. 2009.
[3] X. D. Wang, Y. Y. Duan, W. M. Yan and X. F. Peng, “Local transport
phenomena and cell performance of PEM fuel cells with various
serpentine flow field designs.” J Power Sources, vol. 175, pp. 397–407,
2008.
[4] T. Berning and N. Djilali, “Three-dimensional computational analysis of
transport phenomena in a PEM fuel cell-a parametric study,” J Power Sources, vol. 124, pp. 440-452, 2003.
[5] A. K. Swain, S. A. Billings, P. K. Stansby and M. Baker, “Accurate
prediction of nonlinear wave forces: part Ι fixed cylinder,” Mechanical
system and signal processing, vol. 12, pp.449-485, 1998.
[6] J. Yan, B. Li, H. F. Ling, H. S. Chen, and M. J. Zhang, “Nonlinear State
Space Modeling and System Identification for Electrohydraulic Control,”
Mathematical Problems in Engineering, vol. 2013, pp.1-9, 2013.
[7] L. Ljung and T. Glad. Modeling of dynamic systems. New Jersey; PTR
Prentice-Hall, Inc., 1994.
[8] K. Narenda and K. Parthasarathy, “Identification and control of
dynamical system using neural network,” IEEE Transaction on Neural
network, vol.1 pp4-27, 1990.
[9] S. Haykin, Neural Networks, Second Edition, Pearson Education, 1999.
[10] T. Lin, C. L. Giles, G. B. Horne and S. Y. Kung, “A Delay Damage Model
Selection Algorithm for NARX Neural Networks,” IEEE, Transactions
on Signal Processing, “Special Issue on Neural Networks”, vol. 45, No.
11, pp. 2719-2730, 1997.
[11] H. T. Siegelmann, B. G. Horne and C. L. Giles, “Computational
capabilities of recurrent NARX neural networks,” IEEE Transactions on
Systems, Man and Cybernetics, Part B, vol. 27, No. 2, pp.208-215J, 1997.
[12] M. Basso, L. Giarre, S. Groppi and G. Zappa, “NARX models of an
industrial power plant gas turbine,” IEEE Transaction on Control systems
Technology, vol.13, pp.599-604, 2005.
[13] I. A. Miao, I. S. Stievano and E. G. Canavero, “NARX approach to
black-box modeling of circuit elements,” in Proc. IEEE International
Symposium on Circuits and Systems, pp.411-414, 1998.
[14] H. B. Demuth and M. Beale, Users Guide for the Neural Network
Toolbox for Matlab, The Mathworks, Natica, MA, 1998.
[15] S. J. Cheng, J. J Liu. Nonlinear modeling and identification of proton
exchange membrane fuel cell (PEMFC). Accepted in press, International
Journal of Hydrogen Energy, 2015.