Multi-input and multi-output neural model of the mechanical nonlinear behaviour of a PEM fuel cell system

A fuel cell system model is necessary to prepare and analyse vibration tests. However, in the literature, the mechanical aspect of the fuel cell systems is neglected. In this paper, a neural network modelling approach for the mechanical nonlinear behaviour of a proton exchange membrane (PEM) fuel cell system is proposed. An experimental set is designed for this purpose: a fuel cell system in operation is subjected to random and swept-sine excitations on a vibrating platform in three axes directions. Its mechanical response is measured with three-dimensional accelerometers. The raw experimental data are exploited to create a multi-input and multi-output (MIMO) model using a multi-layer perceptron neural network combined with a time regression input vector. The model is trained and tested. Results from the analysis show good prediction accuracy. This approach is promising because it can be extended to further complex applications. In the future, the mechanical fuel cell system controller will be implemented on a real-time system that provides an environment to analyse the performance and optimize mechanical parameters design of the PEM fuel system and its auxiliaries.

[1]  Stephen Ogaji,et al.  Modelling fuel cell performance using artificial intelligence , 2006 .

[2]  Lars Kai Hansen,et al.  Linear unlearning for cross-validation , 1996, Adv. Comput. Math..

[3]  Ole Henning Sørensen.  Non-linear Pole-placement Control with a Neural Network , 1996, Eur. J. Control.

[4]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[5]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[6]  Daniel R. Lewin,et al.  Model-based Control of Fuel Cells: (1) Regulatory Control , 2004 .

[7]  G. Goodwin,et al.  Modified least squares algorithm incorporating exponential resetting and forgetting , 1988 .

[8]  Song-Yul Choe,et al.  A high dynamic PEM fuel cell model with temperature effects , 2005 .

[9]  P. R. Pathapati,et al.  A new dynamic model for predicting transient phenomena in a PEM fuel cell system , 2005 .

[10]  Niels Kjølstad Poulsen,et al.  Neural Networks for Modelling and Control of Dynamic Systems: A Practitioner’s Handbook , 2000 .

[11]  Jack Brouwer,et al.  Quasi-three dimensional dynamic model of a proton exchange membrane fuel cell for system and controls development , 2007 .

[12]  Luke E. K. Achenie,et al.  Artificial Neural Network Modeling of PEM Fuel Cells , 2005 .

[13]  T. Fuller,et al.  Water and Thermal Management in Solid‐Polymer‐Electrolyte Fuel Cells , 1993 .

[14]  Ralph E. White,et al.  A water and heat management model for proton-exchange-membrane fuel cells , 1993 .

[15]  Luke E. K. Achenie,et al.  A hybrid neural network model for PEM fuel cells , 2005 .

[16]  Mark W. Verbrugge,et al.  A Mathematical Model of the Solid‐Polymer‐Electrolyte Fuel Cell , 1992 .

[17]  D. Wilkinson,et al.  Anode water removal: A water management and diagnostic technique for solid polymer fuel cells , 1995 .

[18]  Ali Feliachi,et al.  Modeling and simulation of the dynamic behavior of a polymer electrolyte membrane fuel cell , 2003 .

[19]  Xianguo Li,et al.  Modelling of polymer electrolyte membrane fuel cells with variable degrees of water flooding , 2000 .

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

[21]  Y. M. Ferng,et al.  Analytical and experimental investigations of a proton exchange membrane fuel cell , 2004 .

[22]  Z. H. Wang,et al.  Two-phase flow and transport in the air cathode of proton exchange membrane fuel cells , 2000 .

[23]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[24]  Ravindra D. Gudi,et al.  Dynamic analysis and linear control strategies for proton exchange membrane fuel cell using a distributed parameter model , 2007 .