0
Research Papers

Artificial Neural Network-Based Model for Calculating the Flow Composition Influence of Solid Oxide Fuel Cell

[+] Author and Article Information
Jarosław Milewski

Associate Professor
e-mail: milewski@itc.pw.edu.pl

Konrad Świrski

Associate Professor
e-mail: swirski@itc.pw.edu.pl
Institute of Heat Engineering,
Faculty of Power and Aeronautical Engineering,
Warsaw University of Technology,
Warsaw 00-665, Poland

1Corresponding author.

Contributed by the Advanced Energy Systems Division of ASME for publication in the JOURNAL OF FUEL CELL SCIENCE AND TECHNOLOGY. Manuscript received November 20, 2012; final manuscript received July 30, 2013; published online December 4, 2013. Editor: Nigel M. Sammes.

J. Fuel Cell Sci. Technol 11(2), 021001 (Dec 04, 2013) (5 pages) Paper No: FC-12-1117; doi: 10.1115/1.4025922 History: Received November 20, 2012; Revised July 30, 2013

The paper presents use of an artificial neural network (ANN) for predicting the thermal-flow behavior of a solid oxide fuel cell with no algorithmic solution merely by utilizing available experimental data. The error backpropagation algorithm was used for an ANN training procedure.

FIGURES IN THIS ARTICLE
<>
Copyright © 2014 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Fig. 1

Results of the training process for 7-8-1 network architecture

Grahic Jump Location
Fig. 2

Results of simulation for the testing data, positive values of voltage are generated only for the hydrogen and carbon monoxide, there are no curves for CO2, N2, and He

Grahic Jump Location
Fig. 3

Results of the training process for 3-4-1 network architecture

Grahic Jump Location
Fig. 4

Results of the simulation for the testing data. Positive values of voltage are generated only for the oxygen, and there is no curve for N2.

Grahic Jump Location
Fig. 5

Results of the training process for 9-3-1 network architecture

Grahic Jump Location
Fig. 6

Results of simulation for the testing data for all flow parameters taken into consideration

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
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