0
Journal of Fuel Cell Science and Technology | Volume 2 | Issue 4 | Research Paper
RESEARCH PAPERS

Artificial Neural Network Modeling of PEM Fuel Cells

[+] Author and Article Information
Shaoduan Ou, Luke E. Achenie

 Department of Chemical Engineering, Unit 3222, 191 Auditorium Road, Storrs, CT 06269

J. Fuel Cell Sci. Technol 2(4), 226-233 (May 23, 2005) (8 pages) doi:10.1115/1.2039951 History: Received April 14, 2004; Revised May 23, 2005
Article
References
Figures
Tables
Citing Articles

Artificial neural network (ANN) approaches for modeling of proton exchange membrane (PEM) fuel cells have been investigated in this study. This type of data-driven approach is capable of inferring functional relationships among process variables (i.e., cell voltage, current density, feed concentration, airflow rate, etc.) in fuel cell systems. In our simulations, ANN models have shown to be accurate for modeling of fuel cell systems. Specifically, different approaches for ANN, including back-propagation feed-forward networks, and radial basis function networks, were considered. The back-propagation approach with the momentum term gave the best results. A study on the effect of Pt loading on the performance of a PEM fuel cell was conducted, and the simulated results show good agreement with the experimental data. Using the ANN model, an optimization model for determining optimal operating points of a PEM fuel cell has been developed. Results show the ability of the optimizer to capture the optimal operating point. The overall goal is to improve fuel cell system performance through numerical simulations and minimize the trial and error associated with laboratory experiments.
FIGURES IN THIS ARTICLE
<>
Copyright © 2005 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
+Feed-forward multilayer neural network with a single hidden layer
View Large  |  Save Figure  |  Download Slide (.ppt)
Feed-forward multilayer neural network with a single hidden layer
Figure 1

Feed-forward multilayer neural network with a single hidden layer

Grahic Jump Location
+Schematic of the applications of the ANN model for PEM fuel cells
View Large  |  Save Figure  |  Download Slide (.ppt)
Schematic of the applications of the ANN model for PEM fuel cells
Figure 2

Schematic of the applications of the ANN model for PEM fuel cells

Grahic Jump Location
+Schematic diagram of the optimization solution
View Large  |  Save Figure  |  Download Slide (.ppt)
Schematic diagram of the optimization solution
Figure 3

Schematic diagram of the optimization solution

Grahic Jump Location
+Experimental and predicted cell voltages for a DMFC running at various operating conditions (data not used for training)
View Large  |  Save Figure  |  Download Slide (.ppt)
Experimental and predicted cell voltages for a DMFC running at various operating conditions (data not used for training)
Figure 4

Experimental and predicted cell voltages for a DMFC running at various operating conditions (data not used for training)

Grahic Jump Location
+Comparison of the simulated result and experimental data for the cell power density (hydrogen feed PEM fuel cell operated at 323K)
View Large  |  Save Figure  |  Download Slide (.ppt)
Comparison of the simulated result and experimental data for the cell power density (hydrogen feed PEM fuel cell operated at 323K)
Figure 10

Comparison of the simulated result and experimental data for the cell power density (hydrogen feed PEM fuel cell operated at 323K)

Grahic Jump Location
+Validation of the ANN model for optimization (hydrogen feed PEM fuel celoperated at 323K)
View Large  |  Save Figure  |  Download Slide (.ppt)
Validation of the ANN model for optimization (hydrogen feed PEM fuel celoperated at 323K)
Figure 9

Validation of the ANN model for optimization (hydrogen feed PEM fuel celoperated at 323K)

Grahic Jump Location
+Comparison of ANN predictions to experimental data from CGFCC
View Large  |  Save Figure  |  Download Slide (.ppt)
Comparison of ANN predictions to experimental data from CGFCC
Figure 8

Comparison of ANN predictions to experimental data from CGFCC

Grahic Jump Location
+ANN predictions of the effects of Pt loading on cell performance
View Large  |  Save Figure  |  Download Slide (.ppt)
ANN predictions of the effects of Pt loading on cell performance
Figure 7

ANN predictions of the effects of Pt loading on cell performance

Grahic Jump Location
+Comparison of different ANN approaches
View Large  |  Save Figure  |  Download Slide (.ppt)
Comparison of different ANN approaches
Figure 6

Comparison of different ANN approaches

Grahic Jump Location
+Comparison of predicted and measured cell polarization curves (temperature: 313.15K, methanol solution flow rate: 5ml∕min, methanol solution concentration: 1M)
View Large  |  Save Figure  |  Download Slide (.ppt)
Comparison of predicted and measured cell polarization curves (temperature: 313.15K, methanol solution flow rate: 5ml∕min, methanol solution concentration: 1M)
Figure 5

Comparison of predicted and measured cell polarization curves (temperature: 313.15K, methanol solution flow rate: 5ml∕min, methanol solution concentration: 1M)

Tables

Errata

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 eBook Content
Network Structures for a Hybrid Approach for Feature Subset Selection Using Neural Networks and Ant Colony Optimization
Intelligent Engineering Systems through Artificial Neural Networks, Volume 16
Estimating Resilient Modulus Using Neural Network Models
Intelligent Engineering Systems Through Artificial Neural Networks, Volume 17
Optimization of Fermentation Media for Wine Lactic Acid Bacteria Using ANN and GA
Intelligent Engineering Systems through Artificial Neural Networks Volume 18
Optimization of Modular Neural Networks with Type-2 Fuzzy Integration Using General Evolutionary Method with Application in Multimodal Biometry
Intelligent Engineering Systems through Artificial Neural Networks
Optimization Model for Smelting Metallic Magnesium by Siliconthermic Reducing Method Based on BP Neural Networks
Proceedings of the International Conference on Technology Management and Innovation
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In