Analysis of the time-varying behavior of a PEM fuel cell stack and dynamical modeling by recurrent neural networks

This work presents an analysis of the time-varying behavior of a PEM fuel cell (PEMFC) stack based on experimental results, pointing out some constraints that should be taken into account in the development of a control system for the stack. A system identification methodology based on recurrent neural networks is proposed to model such behavior. A dynamic model using this technique is developed for a commercial PEMFC stack operating under a real load profile. The results show that the neural model is able to track the stack voltage dynamics with a very low error.

[1]  K. Agbossou,et al.  Online System Identification and Adaptive Control for PEM Fuel Cell Maximum Efficiency Tracking , 2012, IEEE Transactions on Energy Conversion.

[2]  Anna G. Stefanopoulou,et al.  Parameterization and prediction of temporal fuel cell voltage behavior during flooding and drying conditions , 2008 .

[3]  Guoping Liu,et al.  Hybrid model of fuel cell system using wavelet network and PSO algorithm , 2010, 2010 Chinese Control and Decision Conference.

[4]  Jonas Sjöberg,et al.  Neural networks for modelling and control of dynamic systems, M. Nørgaard, O. Ravn, N. K. Poulsen and L. K. Hansen, Springer, London, 2000, xiv+246pp. , 2001 .

[5]  K. Agbossou,et al.  Performance of a stand-alone renewable energy system based on energy storage as hydrogen , 2004, IEEE Transactions on Energy Conversion.

[6]  Caisheng Wang,et al.  Dynamic models and model validation for PEM fuel cells using electrical circuits , 2005 .

[7]  F. Jurado,et al.  Nonlinear model identification of fuel cell power plant , 2004, 2004 IEEE Africon. 7th Africon Conference in Africa (IEEE Cat. No.04CH37590).

[8]  M.A. Choudhry,et al.  Study of a fuel cell power plant in power distribution system. Part I. Dynamic model , 2004, IEEE Power Engineering Society General Meeting, 2004..

[9]  Caisheng Wang,et al.  Power Management of a Stand-Alone Wind/Photovoltaic/Fuel Cell Energy System , 2008, IEEE Transactions on Energy Conversion.

[10]  Haralambos Sarimveis,et al.  Operational optimization and real-time control of fuel-cell systems , 2009 .

[11]  Felix N. Büchi,et al.  Heterogeneous Cell Ageing in Polymer Electrolyte Fuel Cell Stacks , 2009 .

[12]  Carlos Bordons,et al.  Real-Time Implementation of a Constrained MPC for Efficient Airflow Control in a PEM Fuel Cell , 2010, IEEE Transactions on Industrial Electronics.

[13]  Stéphan Astier,et al.  A Large-Signal and Dynamic Circuit Model of a $\hbox{H}_{2}/\hbox{O}_{2}$ PEM Fuel Cell: Description, Parameter Identification, and Exploitation , 2010, IEEE Transactions on Industrial Electronics.

[14]  Vincenzo Piuri,et al.  Neural modeling of dynamic systems with nonmeasurable state variables , 1999, IEEE Trans. Instrum. Meas..

[15]  K. Agbossou,et al.  Control algorithm based on an experimental approach for PEM fuel cell systems efficiency optimization , 2013, 2013 IEEE International Conference on Industrial Technology (ICIT).

[16]  E. H. Watanabe,et al.  A recurrent neural approach for modeling non-reproducible behavior of PEM fuel cell stacks , 2013, 2013 IEEE International Conference on Industrial Technology (ICIT).

[17]  Z. Miao,et al.  Study of a fuel cell power plant in power distribution system. Part II. Stability control , 2004, IEEE Power Engineering Society General Meeting, 2004..