Fuel Cell Output Current Prediction with a Hybrid Intelligent System

A fuel cell is a complex system, which produces electricity through an electrochemical reaction. For the formal application of control strategies on a fuel cell, it is very important to have a precise dynamic model of it. In this paper, a dynamic model of a real hydrogen fuel cell is obtained to predict its response. The data used in this paper to obtain the model have been acquired from a real fuel cell subjected to different load patterns by means of a programmable electronic load. Using this data, a nonlinear model based on a hybrid intelligent system is obtained. This hybrid model uses artificial neural networks to predict the output current of the fuel cell in a very precise way. The use of a hybrid scheme improves the performance of neural networks reducing to half the mean squared error obtained for a global model of the fuel cell.

[1]  José Ramón Hilera González,et al.  Redes neuronales artificiales: fundamentos, modelos y aplicaciones , 1995 .

[2]  José Manuel Andújar Márquez,et al.  Analog Current Control Techniques for Power Control in PEM Fuel-Cell Hybrid Systems: A Critical Review and a Practical Application , 2011, IEEE Transactions on Industrial Electronics.

[3]  José Luís Calvo-Rolle,et al.  Expert condition monitoring on hydrostatic self-levitating bearings , 2013, Expert Syst. Appl..

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

[5]  Francisco Gordillo,et al.  Determining limit cycles in fuzzy control systems , 1997, Proceedings of 6th International Fuzzy Systems Conference.

[6]  Alfonso García-Cerezo,et al.  Fuzzy modeling of a thermal solar plant , 2002, Int. J. Intell. Syst..

[7]  José Manuel Andújar,et al.  A review of energy management strategies for renewable hybrid energy systems with hydrogen backup , 2018 .

[8]  José Luís Calvo-Rolle,et al.  New Climatic Indicators for Improving Urban Sprawl: A Case Study of Tehran City , 2013, Entropy.

[9]  César Echavarría,et al.  BAMBOO-REINFORCED GLULAM BEAMS: AN ALTERNATIVE TO FIBERGLASS-REINFORCED GLULAM BEAMS , 2012 .

[10]  Marcos V. Moreira,et al.  A practical model for evaluating the performance of proton exchange membrane fuel cells , 2009 .

[11]  José Luís Casteleiro-Roca,et al.  Power Cell SOC Modelling for Intelligent Virtual Sensor Implementation , 2017, J. Sensors.

[12]  J. Paska,et al.  Hybrid power systems – An effective way of utilising primary energy sources , 2009 .

[13]  Jean St-Pierre,et al.  Low Cost Electrodes for Proton Exchange Membrane Fuel Cells. Performance in Single Cells and Ballard Stacks. , 1998 .

[14]  Héctor Quintián-Pardo,et al.  A Hybrid Regression System Based on Local Models for Solar Energy Prediction , 2014, Informatica.

[15]  José Manuel Andújar,et al.  A suitable model plant for control of the set fuel cell−DC/DC converter , 2008 .

[16]  José Luís Calvo-Rolle,et al.  Adaptive Inverse Control Using an Online Learning Algorithm for Neural Networks , 2014, Informatica.

[17]  José Luís Calvo-Rolle,et al.  On the monitoring task of solar thermal fluid transfer systems using NN based models and rule based techniques , 2014, Eng. Appl. Artif. Intell..

[18]  José Manuel Andújar Márquez,et al.  A general methodology for online TS fuzzy modeling by the extended Kalman filter , 2014, Appl. Soft Comput..

[19]  Viral S. Mehta,et al.  Review and analysis of PEM fuel cell design and manufacturing , 2003 .

[20]  José Luís Casteleiro-Roca,et al.  Modelling the hypnotic patient response in general anaesthesia using intelligent models , 2018, Log. J. IGPL.

[21]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[22]  D. Ross.  Power struggle [power supplies for portable equipment] , 2003 .

[23]  Szymon Wojciechowski.  A comparison of classification strategies in rule-based classifiers , 2018, Log. J. IGPL.

[24]  Giuseppe Buja,et al.  Development of Electric Propulsion Systems for Light Electric Vehicles , 2011, IEEE Transactions on Industrial Informatics.

[25]  José Manuel Andújar Márquez,et al.  Hardware/Software Data Acquisition System for Real Time Cell Temperature Monitoring in Air-Cooled Polymer Electrolyte Fuel Cells , 2017, Sensors.

[26]  Héctor Quintián-Pardo,et al.  Simplified method based on an intelligent model to obtain the extinction angle of the current for a single-phase half wave controlled rectifier with resistive and inductive load , 2015, J. Appl. Log..

[27]  Basil Mohammed Al-Hadithi,et al.  Formal methodology for analyzing the dynamic behavior of nonlinear systems using fuzzy logic. , 2015 .

[28]  J. C. Amphlett,et al.  A model predicting transient responses of proton exchange membrane fuel cells , 1996 .

[29]  A. Kirubakaran,et al.  A review on fuel cell technologies and power electronic interface , 2009 .

[30]  Manuel Graña,et al.  A novel methodology for clinical semantic annotations assessment , 2018, Log. J. IGPL.

[31]  J. C. Amphlett,et al.  TECHNICAL PAPERS ELECTROCHEMICAL SCIENCE AND TECHNOLOGY Performance Modeling of the Ballard Mark IV Solid Polymer Electrolyte Fuel Cell I. Mechanistic Model Development , 1995 .

[32]  José Manuel Andújar,et al.  Fuel cells: History and updating. A walk along two centuries , 2009 .

[33]  José Luís Casteleiro-Roca,et al.  Modeling the Electromyogram (EMG) of Patients Undergoing Anesthesia During Surgery , 2015, SOCO.

[34]  Michael C. Georgiadis,et al.  Modeling, simulation and experimental validation of a PEM fuel cell system , 2011, Comput. Chem. Eng..

[35]  Jose Luis Calvo Rolle,et al.  APPLICATION OF A LOW COST COMMERCIAL ROBOT IN TASKS OF TRACKING OF OBJECTS , 2012 .

[36]  José Luís Calvo-Rolle,et al.  A hybrid batch SOM-NG algorithm , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[37]  Javier Gonzalo González Fontanet,et al.  Alternativas de control para un Péndulo de Furuta , 2016 .

[38]  Hubertus P.L.H. van Bussel,et al.  Dynamic model of solid polymer fuel cell water management , 1998 .

[39]  Juan Aurelio Montero Sousa,et al.  DESARROLLO DE UN SISTEMA EXPERTO PARA AYUDAR A LA VERIFICACIÓN DEL SISTEMA "TACAN" , 2014 .

[40]  Dong Wei,et al.  Parameter optimization of thermal-model-oriented control law for PEM fuel cell stack via novel genetic algorithm , 2011 .

[41]  Francisco Jesús Martínez-Murcia,et al.  Using deep neural networks along with dimensionality reduction techniques to assist the diagnosis of neurodegenerative disorders , 2018, Log. J. IGPL.

[42]  Jon Lekube,et al.  Mejora de la Potencia Obtenida en Plantas de Generación Undimotriz basadas en Columna de Agua Oscilante , 2018 .

[43]  P. Famouri,et al.  Electrochemical circuit model of a PEM fuel cell , 2003, 2003 IEEE Power Engineering Society General Meeting (IEEE Cat. No.03CH37491).

[44]  Carlos Carrascosa,et al.  Detecting emotions through non-invasive wearables , 2018, Log. J. IGPL.

[45]  José Manuel Andújar,et al.  Step by step development of a real fuel cell system. Design, implementation, control and monitoring , 2015 .

[46]  Esteban Jove,et al.  Hybrid intelligent system to predict the individual academic performance of engineering students , 2018 .

[47]  Isaías García,et al.  Formalization and practical implementation of a conceptual model for PID controller tuning , 2011 .

[48]  José Manuel Andújar,et al.  Modular PEM Fuel Cell SCADA & Simulator System , 2015 .

[49]  Héctor Quintián-Pardo,et al.  A hybrid intelligent system for PID controller using in a steel rolling process , 2013, Expert Syst. Appl..

[50]  Zhihua Yang,et al.  An experimental study on the dynamic process of PEM fuel cell stack voltage , 2011 .

[51]  José Manuel Andújar,et al.  Optimal interface based on power electronics in distributed generation systems for fuel cells , 2011 .

[52]  José Manuel Andújar Márquez,et al.  A General and Formal Methodology to Design Stable Nonlinear Fuzzy Control Systems , 2009, IEEE Transactions on Fuzzy Systems.

[53]  José Manuel Andújar,et al.  From the cell to the stack. A chronological walk through the techniques to manufacture the PEFCs core , 2018, Renewable and Sustainable Energy Reviews.

[54]  José Manuel Andújar,et al.  Metodología formal de análisis del comportamiento dinámico de sistemas no lineales mediante lógica borrosa , 2015 .

[55]  J. C. Amphlett.  Performance Modeling of the Ballard Mark IV Solid Polymer Electrolyte Fuel Cell , 1995 .

[56]  Jose Luis Calvo Rolle,et al.  CONTROLADOR NEURO-ROBUSTO PARA SISTEMAS NO LINEALES , 2011 .

[57]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[58]  C. Chamberlin,et al.  Modeling of Proton Exchange Membrane Fuel Cell Performance with an Empirical Equation , 1995 .

[59]  José Luís Casteleiro-Roca,et al.  Bio-inspired model of ground temperature behavior on the horizontal geothermal exchanger of an installation based on a heat pump , 2015, Neurocomputing.

[60]  José Antonio López-Vázquez,et al.  Attempts Prediction by Missing Data Imputation in Engineering Degree , 2017, SOCO-CISIS-ICEUTE.

[61]  Eloy Irigoyen,et al.  A NARX neural network model for enhancing cardiovascular rehabilitation therapies , 2013, Neurocomputing.

[62]  José Manuel Andújar,et al.  Air-cooled fuel cells: Keys to design and build the oxidant/cooling system , 2018, Renewable Energy.