Here, we present a new procedure to evaluate thermodynamic properties of magnetocaloric materials based on Artificial Neural Networks (ANNs). This methodology has been developed to speed up the characterisation of new magnetocaloric materials and facilitate the design process for a magnetic refrigerator. Indeed, it requires a small amount of experimental data to characterise an MCM accurately, in comparison with other commonly-used techniques.
Three different codes are provided to run the procedure. The first code is related to the training of the ANN starting from the experimental data. The second code allows to use the evaluation method within an AMR numerical simulation model. The last code provides a database of the thermodynamic properties of magnetocaloric materials, based on the learning capabilities of the Artificial Neural Networks.
Please check the README file for further information.
Maiorino, Angelo, et al. “Evaluating Magnetocaloric Effect in Magnetocaloric Materials: A Novel Approach Based on Indirect Measurements Using Artificial Neural Networks.” Energies, vol. 12, no. 10, MDPI AG, May 2019, p. 1871, doi:10.3390/en12101871.
MATLAB Release Compatibility
Platform CompatibilityWindows macOS Linux
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!Start Hunting!