A dataset for validation of artifical neural network models for SOFC

Published: 11 January 2021| Version 1 | DOI: 10.17632/j8b9v4cb9d.1
Contributors:
Vanja Subotic,
Michael Eibl,
Christoph Hochenauer

Description

The data sets shown here include voltage and current values from polarization curves, which are gained from experimental tests performed on SOFCs as well as the data generated employing a multi-physic model for SOFCs. The same data set is used to validate the computed data from the publication "Artificial intelligence for time-efficient prediction and optimization of solid oxide fuel cell performances", volume 230, 113764, published in Energy Conversion and Management. If the researchers use these data to develop and validate new networks and models, please cite the following studies: (1) Artificial intelligence for time-efficient prediction and optimization of solid oxide fuel cell performances, Energy Conversion and Management (230), 2021, DOI: https://doi.org/10.​1016/​j.​enconman.​2020.​113764 (2) Performance assessment of industrial-sized solid oxide cells operated in a reversible mode: Detailed numerical and experimental study, International Journal of Hydrogen Energy 45 (53), 2020, DOI: https://doi.org/10.1016/j.ijhydene.2020.07.165. The data are available as .txt files, in which the operating current density, operating temperature, and voltage are presented. The temperature is varied between 750, 775, 800, and 825°C. The fuel used contains hydrogen, steam, and nitrogen. The volume fractions of the individual components are given in the document title.

Files