ORALS
SESSION:
SISAMSatAM-R3
G: Nanoscale(s) | Kobe International Symposium on Science of Innovative and Sustainable Alloys and Magnets (5th Intl. Symp. on Science of Intelligent and Sustainable Advanced Materials (SISAM)) |
| Sat Oct, 26 2019 / Room: Dr. Christian Bernard | |
| Session Chairs: Ludwig Schultz; Session Monitor: TBA |
12:10: [SISAMSatAM03]
Machine learning for permanent magnet optimization Thomas
Schrefl1 ;
1Danube University Krems, Wiener Neustadt, Austria;
Paper Id: 33
[Abstract] In addition to the intrinsic magnetic properties, the microstructure is of utmost importance for the performance of a permanent magnet. We show how to use machine learning methods in order obtain a deeper understanding of the influence of the granular structure on the coercive field of permanent magnets. Using machine learning, we can identify the weak spots in a magnet where magnetization reversal is initiated. Tailored improvement of the magnet's structure or the intrinsic magnetic properties at regions where the switching field was identified to be low can sufficiently improve the magnet.
Work supported by the European Union's Horizon 2020 NMBP23-2015 research No 686056.
References:
Fischbacher, J., Kovacs, A., Gusenbauer, M., Oezelt, H., Exl, L., Bance, S., & Schrefl, T. (2018). Micromagnetics of rare-earth efficient permanent magnets. Journal of Physics D: Applied Physics, 51(19), 193002.
Exl, L., Fischbacher, J., Kovacs, A., Oezelt, H., Gusenbauer, M., Yokota, K., ... & Schrefl, T. (2018). Magnetic microstructure machine learning analysis. Journal of Physics: Materials, 2(1), 014001.
