Hybrid model of fuel cell system using wavelet network and PSO algorithm

Fuel cell power system has attracted significant attentions from many researchers. A fuel cell system model, which is accurate and applicable in engineering practice, plays a key role in controller design, fault diagnosis and power management for fuel cell power systems. In this paper, a hybrid model of a Polymer Electrolyte Membrane Fuel Cell (PEMFC) power system is proposed. The hybrid model contains a mechanism submodel and a black-box submodel. The adjustable parameters in the mechanism submodel are optimized using PSO algorithm. The black-box submodel is expressed in NARX form, which is approximated by a wavelet network using the real test data. From practical experiments, it is shown that, the hybrid model acceptably approximates the practical system. This hybrid PEMFC model can be used for mass flow controller design, fault diagnosis and power management.

[1]  T. Springer,et al.  Polymer Electrolyte Fuel Cell Model , 1991 .

[2]  Luciane Neves Canha,et al.  An electrochemical-based fuel-cell model suitable for electrical engineering automation approach , 2004, IEEE Transactions on Industrial Electronics.

[3]  Senchun Chai,et al.  Intelligent control for improvements in PEM fuel cell flow performance , 2008, Int. J. Autom. Comput..

[4]  Stephen A. Billings,et al.  Lattice Dynamical Wavelet Neural Networks Implemented Using Particle Swarm Optimization for Spatio–Temporal System Identification , 2009, IEEE Transactions on Neural Networks.

[5]  Pierre R. Roberge,et al.  Development and application of a generalised steady-state electrochemical model for a PEM fuel cell , 2000 .

[6]  George Andreadis,et al.  A model-based parametric analysis of a direct ethanol polymer electrolyte membrane fuel cell performance , 2009 .

[7]  Guo-Ping Liu,et al.  Modelling of a PEM Fuel Cell System , 2008 .

[8]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[9]  Michael Buchholz,et al.  Modelling PEM fuel cell stacks for FDI using linear subspace identification , 2008, 2008 IEEE International Conference on Control Applications.

[10]  R. W. Dobbins,et al.  Computational intelligence PC tools , 1996 .

[11]  Jaroslaw Sobieszczanski-Sobieski,et al.  Multidisciplinary optimization of a transport aircraft wing using particle swarm optimization , 2002 .

[12]  R. Eberhart,et al.  Comparing inertia weights and constriction factors in particle swarm optimization , 2000, Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512).

[13]  James Kennedy,et al.  The particle swarm: social adaptation of knowledge , 1997, Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97).

[14]  R. Eberhart,et al.  Empirical study of particle swarm optimization , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[15]  J. C. Amphlett,et al.  Performance modeling of the Ballard Mark IV solid polymer electrolyte fuel cell. II: Empirical model development , 1995 .

[16]  Wang Hongyan,et al.  Robust output feedback control of electro- hydraulic servo system using wavelet neural network , 2009, 2009 Chinese Control and Decision Conference.

[17]  M.H. Nehrir,et al.  Dynamic models and model validation for PEM fuel cells using electrical circuits , 2005, IEEE Transactions on Energy Conversion.

[18]  Li Xiao-yi,et al.  Wavelet neural network predication for epidemic outbreak , 2009, 2009 Chinese Control and Decision Conference.

[19]  Anna G. Stefanopoulou,et al.  Modeling and control for PEM fuel cell stack system , 2002, Proceedings of the 2002 American Control Conference (IEEE Cat. No.CH37301).

[20]  Changjun Zhu,et al.  ANN based on PSO for surface water quality evaluation model and its application , 2009, 2009 Chinese Control and Decision Conference.

[21]  Qinghua Zhang,et al.  Using wavelet network in nonparametric estimation , 1997, IEEE Trans. Neural Networks.

[22]  S. Rael,et al.  Mathematical model and characterization of the transient behavior of a PEM fuel cell , 2004, IEEE Transactions on Power Electronics.

[23]  Qinghua Zhang,et al.  Wavelet networks , 1992, IEEE Trans. Neural Networks.