Article: Application of Neural Network approach for Proton Exchange Membrane fuel cell systems Journal: International Journal of Intelligent Systems Technologies and Applications (IJISTA) 2009 Vol.6 No.1/2 pp.89 - 111 Abstract: Artificial Intelligence (AI) techniques, particularly the Neural Networks (NNs), are recently having significant impact on power electronics. In a Proton Exchange Membrane (PEM) fuel cell system, there is a strong relationship between the available electrical power and the actual operating conditions: gas conditioning, membrane hydration state, temperature, current set point, etc. Thus, a |minimal behavioural model| of a fuel cell system able to evaluate the output variables and their variations is highly interesting. In this paper, we are interested in controlling the powers by using Neural Networks Controllers under the assumption that any system of production is subjected permanently to load steps change variations. So a static production system including a Proton Exchange Membrane Fuel Cell (PEMFC) is subjected to variations of active and reactive power. Then, the goal is to make the system follows these imposed variations. In this work, a PEM fuel cell NN model is proposed using a quasi-Newton method and implemented on Matlab/Simulink<SUP align="right">®</SUP> software, Levenberg-Marquardt training algorithm, activation functions and their causes on the effectiveness of the performance modelling are discussed, the quasi-Newton NN control is described and results from the analysis as well as the limitations of the approach are presented. Inderscience Publishers - linking academia, business and industry through research

Title: Application of Neural Network approach for Proton Exchange Membrane fuel cell systems

Authors: Mustapha Hatti, Mustapha Tioursi

Addresses: Thermohydraulic Department, Division of Nuclear Technology, Nuclear Research Center of Birine, B.P 180 Ain Oussera, Djelfa, Algeria. ' Department of Electrical Engineering, University of Sciences and Technology of Oran, B P 1505 El M'naouer Oran 31000, Algeria

Abstract: Artificial Intelligence (AI) techniques, particularly the Neural Networks (NNs), are recently having significant impact on power electronics. In a Proton Exchange Membrane (PEM) fuel cell system, there is a strong relationship between the available electrical power and the actual operating conditions: gas conditioning, membrane hydration state, temperature, current set point, etc. Thus, a |minimal behavioural model| of a fuel cell system able to evaluate the output variables and their variations is highly interesting. In this paper, we are interested in controlling the powers by using Neural Networks Controllers under the assumption that any system of production is subjected permanently to load steps change variations. So a static production system including a Proton Exchange Membrane Fuel Cell (PEMFC) is subjected to variations of active and reactive power. Then, the goal is to make the system follows these imposed variations. In this work, a PEM fuel cell NN model is proposed using a quasi-Newton method and implemented on Matlab/Simulink^® software, Levenberg-Marquardt training algorithm, activation functions and their causes on the effectiveness of the performance modelling are discussed, the quasi-Newton NN control is described and results from the analysis as well as the limitations of the approach are presented.

Keywords: dynamic modelling; NNC; neural network controllers; PEM fuel cells; neural networks; proton exchange membrane; output variables; performance modelling; power electronics.

DOI: 10.1504/IJISTA.2009.022690

International Journal of Intelligent Systems Technologies and Applications, 2009 Vol.6 No.1/2, pp.89 - 111

Published online: 25 Jan 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Application of Neural Network approach for Proton Exchange Membrane fuel cell systems

Keep up-to-date