Performance prediction of a proton exchange membrane fuel cell using the ANFIS model

Abstract In this study, the performance (current–voltage curve) prediction of a Proton Exchange Membrane Fuel Cell (PEMFC) is performed for different operational conditions using an Adaptive Neuro-Fuzzy Inference System (ANFIS). First, ANFIS is trained with a set of input and output data. The trained model is then tested with an independent set of experimental data. The trained and tested model is then used to predict the performance curve of the PEMFC under various operational conditions. The model shows very good agreement with the experimental data and this indicates that ANFIS is capable of predicting fuel cell performance (in terms of cell voltage) with a high accuracy in an easy, rapid and cost effective way for the case presented. Finally, the capabilities and the limitations of the model for the application in fuel cells have been discussed.

[1]  Yan Si-jia,et al.  Modelling and control PEMFC using fuzzy neural networks , 2005 .

[2]  Chunwen Li,et al.  Modeling of a 5-cell direct methanol fuel cell using adaptive-network-based fuzzy inference systems , 2008 .

[3]  Francisco Jurado,et al.  Predictive control of solid oxide fuel cells using fuzzy Hammerstein models , 2006 .

[4]  Xin-Jian Zhu,et al.  Short communication Modeling a SOFC stack based on GA-RBF neural networks identification , 2007 .

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

[6]  Marian B. Gorzalczany.  Computational Intelligence Systems and Applications - Neuro-Fuzzy and Fuzzy Neural Synergisms , 2002, Studies in Fuzziness and Soft Computing.

[7]  Xiangyang Zhou,et al.  Mathematical analysis of planar solid oxide fuel cells , 2008 .

[8]  Guido Bugmann,et al.  NEURAL NETWORK DESIGN FOR ENGINEERING APPLICATIONS , 2001 .

[9]  Dennis Y.C. Leung,et al.  Mathematical modeling of ammonia-fed solid oxide fuel cells with different electrolytes , 2008 .

[10]  J.-S.R. Jang,et al.  Input selection for ANFIS learning , 1996, Proceedings of IEEE 5th International Fuzzy Systems.

[11]  Abdellah El Moudni,et al.  Dynamic modeling and water management in proton exchange membrane fuel cell , 2008 .

[12]  Jaime Arriagada,et al.  Artificial neural network simulator for SOFC performance prediction , 2002 .

[13]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[14]  Lin Wang,et al.  A parametric study of PEM fuel cell performances , 2003 .

[15]  Frano Barbir,et al.  PEM Fuel Cells , 2006 .

[16]  Chuen-Tsai Sun,et al.  Neuro-fuzzy modeling and control , 1995, Proc. IEEE.

[17]  Evgueniy Entchev,et al.  Application of adaptive neuro-fuzzy inference system techniques and artificial neural networks to predict solid oxide fuel cell performance in residential microgeneration installation , 2007 .