A Neural Inverse Control of a PEM-FC System by the Generalized Mapping Regressor (GMR)

This paper deals with the air management subsystem in fuel cell systems (FCS). It proposes to use a feedforward control action for improving a classical PI control of the FCS for preventing oxygen starvation by using the control scheme suggested by Kawato. This paper therefore, proposes the application of a recent neural network scheme, the GMR (Generalized Mapping Regressor Mapping) to implement a static feedforward controller, which is obtained with the inversion of the FCS model. The idea, for the air management subsystem, is to use a feedforward for optimising a classical PI control of the FCS for preventing oxygen starvation. This control system has been implemented both in numerical simulation and experimentally adopting a properly devised FCS in which the FC stack is realized by a buck-converter (emulator), that is by using a hardware-in-the-loop experimental rig.

[1]  A.G. Stefanopoulou,et al.  Control of fuel cell breathing , 2004, IEEE Control Systems.

[2]  Anna G. Stefanopoulou,et al.  Control of Fuel Cell Power Systems , 2004 .

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

[4]  Akinori Tsukada,et al.  DYNAMICS OF THE POLYMER ELECTROLYTE FUEL CELL: EXPERIMENTS AND MODEL-BASED ANALYSIS , 2008 .

[5]  Maurizio Cirrincione,et al.  A Neural Non-linear Predictive Control for PEM-FC JES , 2005 .

[6]  Slobodan Cuk,et al.  A general unified approach to modelling switching-converter power stages , 1976, 1970 IEEE Power Electronics Specialists Conference.

[7]  Anna G. Stefanopoulou,et al.  Current Management in a Hybrid Fuel Cell Power System: A Model-Predictive Control Approach , 2006, IEEE Transactions on Control Systems Technology.

[8]  Xiongwen Zhang,et al.  Nonlinear model predictive control based on the moving horizon state estimation for the solid oxide fuel cell , 2008 .

[9]  A.C. Rufer,et al.  An Analytical, Control-Oriented State Space Model for a PEM Fuel Cell System , 2007, 2007 Power Conversion Conference - Nagoya.

[10]  M.G. Simoes,et al.  Neural optimal control of PEM fuel cells with parametric CMAC networks , 2003, IEEE Transactions on Industry Applications.

[11]  Per Printz Madsen.  Neural network for optimization of existing control systems , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[12]  M. Cirrincione,et al.  Real time simulation of renewable sources by model-based control of DC/DC converters , 2008, 2008 IEEE International Symposium on Industrial Electronics.

[13]  Hossin Hosseinian,et al.  Power Electronics , 2020, 2020 27th International Conference on Mixed Design of Integrated Circuits and System (MIXDES).

[14]  Paul Hendrik Rodatz,et al.  Dynamics of the polymer electrolyte fuel cell , 2003 .

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

[16]  Marcelo Godoy Simões,et al.  Simulation of fuel-cell stacks using a computer-controlled power rectifier with the purposes of actual high-power injection applications , 2003 .

[17]  H. Venable,et al.  THE K FACTOR : A NEW MATHEMATICAL TOOL FOR STABILITY ANALYSIS AND SYNTHESIS , 2022 .

[18]  Lino Guzzella,et al.  Optimizing air supply control of a PEM fuel cell system , 2003, Proceedings of the 2003 American Control Conference, 2003..

[19]  Mitsuo Kawato,et al.  Feedback-Error-Learning Neural Network for Supervised Motor Learning , 1990 .

[20]  Huei Peng,et al.  Model predictive control for starvation prevention in a hybrid fuel cell system , 2004, Proceedings of the 2004 American Control Conference.