0
Research Papers

# Prediction of Direct Methanol Fuel Cell Stack Performance Using Artificial Neural Network

[+] Author and Article Information
M. A. Rafe Biswas

Department of Mechanical Engineering,
University of Texas at Tyler,
Tyler, TX 75799
e-mail: mbiswas@uttyler.edu

Melvin D. Robinson

Department of Electrical Engineering,
University of Texas at Tyler,
Tyler, TX 75799
e-mail: mrobinson@uttyler.edu

1Corresponding author.

Manuscript received December 14, 2016; final manuscript received April 30, 2017; published online June 21, 2017. Assoc. Editor: Matthew Mench.

J. Electrochem. En. Conv. Stor. 14(3), 031008 (Jun 21, 2017) (7 pages) Paper No: JEECS-16-1162; doi: 10.1115/1.4036811 History: Received December 14, 2016; Revised April 30, 2017

## Abstract

A direct methanol fuel cell (DMFC) converts liquid fuel into electricity to power devices, while operating at relatively low temperatures and producing virtually no greenhouse gases. Since DMFC performance characteristics are inherently complex, it can be postulated that artificial neural networks (NN) represent a marked improvement in prediction capabilities. In this work, an artificial NN is employed to predict the performance of a DMFC under various operating conditions. Input variables for the analysis consist of methanol concentration, temperature, current density, number of cells, and anode flow rate. The addition of the two latter variables allows for a more distinctive model when compared to prior NN models. The key performance indicator of our NN model is cell voltage, which is an average voltage across the stack and ranges from 0 to 0.8 V. Experimental studies were conducted using DMFC stacks with membrane electrode assemblies consisting of an additional unique liquid barrier layer to minimize water loss to atmosphere. To determine the best fit to the experimental data, the model is trained using two second-order training algorithms: OWO-Newton and Levenberg–Marquardt (LM). The topology of OWO-Newton algorithm is slightly different from that of LM algorithm by employing bypass weights. The application of NN shows rapid construction of a predictive model of cell voltage for varying operating conditions with an accuracy on the order of $10−4$, which can be comparable to literature. The coefficient of determination of the optimal model results using either algorithm were greater than 0.998.

<>

## References

O'hayre, R. , Cha, S. , Colella, W. , and Prinz, F. , 2005, Fuel Cell Fundamentals, Wiley, New York.
Biswas, M. , Mudiraj, S. , Lear, W. , and Crisalle, O. , 2014, “ Systematic Approach for Modeling Methanol Mass Transport on the Anode Side of Direct Methanol Fuel Cells,” Int. J. Hydrogen Energy, 39(15), pp. 8009–8025.
Mudiraj, S. , Crisalle, O. D. , Biswas, M. , and Lear, W. , 2015, “ Comprehensive Mass Transport Modeling Technique for the Cathode Side of an Open-Cathode Direct Methanol Fuel Cell,” Int. J. Hydrogen Energy, 40(25), pp. 8137–8159.
Wang, R. , Qi, L. , Xie, X. , Ding, Q. , Li, C. , and Ma, C. M. , 2008, “ Modeling of a 5-Cell Direct Methanol Fuel Cell Using Adaptive-Network-Based Fuzzy Inference Systems,” J. Power Sources, 185(2), pp. 1201–1208.
Weber, A. Z. , and Newman, J. , 2004, “ Transport in Polymer-Electrolyte Membranes—II: Mathematical Model,” J. Electrochem. Soc., 151(2), pp. A311–A325.
Fuller, T. F. , and Newman, J. , 1992, “ Experimental Determination of the Transport Number of Water in Nafion 117 Membrane,” J. Electrochem. Soc., 139(5), pp. 1332–1337.
Weber, A. Z. , and Newman, J. , 2003, “ Transport in Polymer-Electrolyte Membranes—I: Physical Model,” J. Electrochem. Soc., 150(7), pp. A1008–A1015.
Gandomi, Y. A. , Zawodzinski, T. A. , and Mench, M. M. , 2014, “ Concentrated Solution Model of Transport in All Vanadium Redox Flow Battery Membrane Separator,” ECS Trans., 61(13), pp. 23–32.
Gandomi, Y. A. , Aaron, D. , Zawodzinski, T. , and Mench, M. , 2016, “ In Situ Potential Distribution Measurement and Validated Model for All-Vanadium Redox Flow Battery,” J. Electrochem. Soc., 163(1), pp. A5188–A5201.
Henken, J. , and Biswas, M. A. R. , 2015, “ Validation of Neural Network Model for Residential Energy Consumption,” ASEE Gulf Southwest Annual Conference (GSW), San Antonio, TX, Mar. 25–27, p. 90.
Tafazoli, M. , Baseri, H. , Alizadeh, E. , and Shakeri, M. , 2013, “ Modeling of Direct Methanol Fuel Cell Using the Artificial Neural Network,” ASME J. Fuel Cell Sci. Technol., 10(4), p. 041007.
Pajaei, H. S. , Abbasian, S. , and Mehdizadeh, B. , 2012, “ Prediction of Direct Methanol Fuel Cell Using Artificial Neural Network,” Asian J. Chem., 24(11), pp. 5413–5414.
Ge, J. , and Liu, H. , 2005, “ Experimental Studies of a Direct Methanol Fuel Cell,” J. Power Sources, 142(1–2), pp. 56–69.
Cao, L. Z. , Su, Z. L. , and Li, C. W. , 2012, “ Design and Performance Analysis of Direct Methanol Fuel Cell,” Advanced Materials Research, Vol. 403, Trans Tech Publications, Zurich, Switzerland, pp. 4030–4035.
Chang, K.-Y. , Chang, C.-Y. , Wang, W.-J. , and Chen, C.-Y. , 2012, “ Modeling Polarization of a Dmfc System Via Neural Network With Immune-Based Particle Swarm Optimization,” Int. J. Green Energy, 9(4), pp. 309–321.
Mossman, A. , and Olmeijer, D. , 2008, “ Composite Polymer Electrolyte Membranes,” Polyfuel, Inc., Mountain View, CA, U.S. Patent No. US20100279198 A1.
Mossman, A. , Wells, B. , and Barton, R. , 2007, “ Gas Phase Fuel Cells,” Polyfuel Inc, Mountatin View, CA, U.S. Patent No. WO2007131229 A3.
Mossman, A. , Wells, B. , Barton, R. , and Voss, H. , 2007, “ Passive Recovery of Liquid Water Produced by Fuel Cells,” University Of North Florida Board Of Trustees, Jacksonville, FL, U.S. Patent No. US8298719 B2.
Fuel Cell Technologies, 2009, “ Fuel Cell Test Stations,” Fuel Cell Technologies, Albuquerque, NM, accessed June 2, 2017,
Labview, 2008, “ National Instruments,” Labview, Austin, TX.
Miao, Q. , Cao, G.-Y. , and Zhu, X.-J. , 2007, “ Performance Analysis and Fuzzy Neural Networks Modeling of Direct Methanol Fuel Cell,” J. Shanghai Univ., 11(1), pp. 84–87.
Saarinen, S. , Bramley, R. , and Cybenko, G. , 1993, “ ILL-Conditioning in Neural Network Training Problems,” SIAM J. Sci. Comput., 14(3), pp. 693–714.
Wille, J. , 1997, “ On the Structure of the Hessian Matrix in Feedforward Networks and Second Derivative Methods,” International Conference on Neural Networks (ICNN), Houston, TX, June 12, Vol. 3, pp. 1851–1855.
Robinson, M. D. , and Manry, M. T. , 2013, “ Two-Stage Second Order Training in Feedforward Neural Networks,” 26th International Florida Artificial Intelligence Research Society Conference (FLAIRS), St. Pete Beach, FL, May 22–24, pp. 130–135.
Dennis, J. E., Jr. , and Schnabel, R. B. , 1996, Numerical Methods for Unconstrained Optimization and Nonlinear Equations (Classics in Applied Mathematics, Vol. 16), SIAM, Philadelphia, PA.

## Figures

Fig. 1

Schematic of the DMFC cell used in the experimental setup

Fig. 2

VI curve of a four-cell DMFC stack under a steady-state operating condition

Fig. 3

Illustration of a generic fully connected multilayer perceptron

Fig. 4

Comparison of model VI curves to experimental data of a four-cell DMFC stack where NN models are based on OWO-Newton and LM

Fig. 5

Comparison of model and experimental VI curves of an eight-cell DMFC stack where NN models are based on OWO-Newton and LM

Fig. 6

Experimental and NN-based OWO-Newton model curves of a four-cell DMFC for operating temperatures of 45 °C and 60 °C

Fig. 7

Experimental and NN-based LM Model curves of a four-cell DMFC for operating temperatures of 45 °C and 60 °C

Fig. 8

Experimental and NN-based OWO-Newton model curves of a four-cell DMFC for operating methanol concentration of 1 M and 1.5 M

Fig. 9

Experimental and NN-based LM Model curves of a four-cell DMFC for operating methanol concentration of 1 M and 1.5 M

## Discussions

Some tools below are only available to our subscribers or users with an online account.

### Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related Proceedings Articles
Related eBook Content
Topic Collections