Extracting local nucleation fields in permanent magnets using machine learning
Source abstract
Abstract
Abstract Microstructural features play an important role in the quality of permanent magnets. The coercivity is greatly influenced by crystallographic defects, like twin boundaries, as is well known for MnAl-C. It would be very useful to be able to predict the macroscopic coercivity from microstructure imaging. Although this is not possible now, in the present work we examine a related question, namely the prediction of simulated nucleation fields of a quasi-three-dimensional (rescaled and extruded) system constructed from a two-dimensional image. We extract features of the image and analyze them via machine learning. A large number of extruded systems are constructed from 10 × 10 pixel sub-images of an Electron Backscatter Diffraction (EBSD) image using an automated meshing procedure. A local nucleation field is calculated by micromagnetic simulation of each quasi-three-dimensional system. Decision trees, trained with the simulation results, can predict nucleation fields of these quasi-three-dimensional systems from new images within seconds. As for now we cannot quantitatively predict the macroscopic coercivity, nevertheless we can identify weak spots in the magnet and see trends in the nucleation field distribution.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Magnetic Properties of Alloys · Magnetic Properties and Applications · Magnetic properties of thin films
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (36)
Show source-provided references
1. Skokov, K. & Gutfleisch, O. Heavy rare earth free, free rare earth and rare earth free magnets-vision and reality. Scripta Materialia 154, 289–294 (2018).10.1016/j.scriptamat.2018.01.032 ↗
2. Coey, J. Permanent magnets: plugging the gap. Scripta Materialia 67, 524–529 (2012).10.1016/j.scriptamat.2012.04.036 ↗
3. Landuyt, J. V., Tendeloo, G., Broek, J., Donkersloot, H. & Zijlstra, H. Defect structure and magnetic properties of MnAl permanent magnet materials. IEEE Trans. Magn. 14, 679–681 (1978).10.1109/TMAG.1978.1059949 ↗
4. Houseman, E. & Jakubovics, J. Domain structure and magnetization processes in mnal and mnalc alloys. J. Magn. Magn. Mater. 31, 1005–1006 (1983).10.1016/0304-8853(83)90770-9 ↗
5. Yanar, C., Radmilovic, V., Soffa, W. A. & Wiezorek, J. M. Evolution of microstructure and defect structure in l10-ordered manganese aluminide permanent magnet alloys. Intermetallics 9, 949–954 (2001).10.1016/S0966-9795(01)00095-4 ↗
6. Bittner, F., Schultz, L. & Woodcock, T. G. Twin-like defects in L10 ordered τ -MnAl-C studied by EBSD. Acta Materialia 101, 48–54 (2015).10.1016/j.actamat.2015.08.044 ↗
7. Palanisamy, D., Raabe, D. & Gault, B. On the compositional partitioning during phase transformation in a binary ferromagnetic mnal alloy. Acta Materialia 174, 227–236 (2019).10.1016/j.actamat.2019.05.037 ↗
8. Kronmüller, H. & Goll, D. Micromagnetism of advanced hard magnetic materials. Int. J. Mater. Res. 100, 640–651 (2009).10.3139/146.110092 ↗
9. Fischbacher, J. et al. Micromagnetics of rare-earth efficient permanent magnets. J. Phys. D Appl. Phys. 51, 193002 (2018).10.1088/1361-6463/aab7d1 ↗
10. Schabes, M. E. Micromagnetic theory of non-uniform magnetization processes in magnetic recording particles. J. Magn. Magn. Mater. 95, 249–288 (1991).10.1016/0304-8853(91)90225-Y ↗
11. Schwartz, A. J., Kumar, M., Adams, B. L. & Field, D. P. in Electron Backscatter Diffraction in Materials Science, vol. 2 (Springer, 2009).10.1007/978-0-387-88136-2 ↗
12. Sepehri-Amin, H., Ohkubo, T. & Hono, K. Micromagnetic simulations of magnetization reversals in nd-fe-b based permanent magnets. Mater. Trans. 57, 1221–1229 (2016).10.2320/matertrans.M2015457 ↗
13. Sepehri-Amin, H., Ohkubo, T., Gruber, M., Schrefl, T. & Hono, K. Micromagnetic simulations on the grain size dependence of coercivity in anisotropic nd-fe-b sintered magnets. Scripta Materialia 89, 29–32 (2014).10.1016/j.scriptamat.2014.06.020 ↗
14. Bance, S., Bittner, F., Woodcock, T. G., Schultz, L. & Schrefl, T. Role of twin and anti-phase defects in MnAl permanent magnets. Acta Materialia 131, 48–56 (2017).10.1016/j.actamat.2017.04.004 ↗
15. Exl, L. et al. Preconditioned nonlinear conjugate gradient method for micromagnetic energy minimization. Comput. Phys. Commun. 235, 179–186 (2019).10.1016/j.cpc.2018.09.004 ↗
16. Tsukahara, H., Iwano, K., Mitsumata, C., Ishikawa, T. & Ono, K. Micromagnetic simulation for the magnetization reversal process of nd-fe-b hot-deformed nanocrystalline permanent magnets. AIP Adv. 7, 056234 (2017).10.1063/1.4978645 ↗
17. Suess, D. et al. Time resolved micromagnetics using a preconditioned time integration method. J. Magn. Magn. Mater. 248, 298–311 (2002).10.1016/S0304-8853(02)00341-4 ↗
18. Exl, L. et al. Magnetic microstructure machine learning analysis. J. Phys. Mater. 2, 014001 (2018).
19. Dimiduk, D. M., Holm, E. A. & Niezgoda, S. R. Perspectives on the impact of machine learning, deep learning, and artificial intelligence on materials, processes, and structures engineering. Integ. Mater. Manufact. Innovation 7, 157–172 (2018).10.1007/s40192-018-0117-8 ↗
20. Butler, K. T., Davies, D. W., Cartwright, H., Isayev, O. & Walsh, A. Machine learning for molecular and materials science. Nature 559, 547–555 (2018).10.1038/s41586-018-0337-2 ↗
21. Azimi, S. M., Britz, D., Engstler, M., Fritz, M. & Mücklich, F. Advanced steel microstructural classification by deep learning methods. Sci. Rep. 8, 2128 (2018).10.1038/s41598-018-20037-5 ↗
22. Orme, A. D. et al. Insights into twinning in mg az31: A combined ebsd and machine learning study. Comput. Mater. Sci. 124, 353–363 (2016).10.1016/j.commatsci.2016.08.011 ↗
23. Gusenbauer, M. et al. Automated meshing of electron backscatter diffraction data and application to finite element micromagnetics. J. Magn. Magn. Mater. 486, 165256 (2019).10.1016/j.jmmm.2019.165256 ↗
24. Géron, A. in Hands-on Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems ("O’Reilly Media, Inc.", 2017).
25. Reif, M. & Shafait, F. Efficient feature size reduction via predictive forward selection. Pattern Recogn. 47, 1664–1673 (2014).10.1016/j.patcog.2013.10.009 ↗
26. Hastie, T., Tibshirani, R. & Friedman, J. inThe Elements of Statistical Learning: Data Mining, Inference, and Prediction (Springer Science & Business Media, 2009).10.1007/978-0-387-84858-7 ↗
27. Fox, J. in Applied Regression Analysis and Generalized Linear Models (Sage Publications, 2015).
28. Schrefl, T., Schmidts, H., Fidler, J. & Kronmüller, H. The role of exchange and dipolar coupling at grain boundaries in hard magnetic materials. J. Magn. Magn. Mater. 124, 251–261 (1993).10.1016/0304-8853(93)90123-J ↗
29. Abramowitz, G. et al. Neural error regression diagnosis (nerd): a tool for model bias identification and prognostic data assimilation. J. Hydrometeorol. 7, 160–177 (2006).10.1175/JHM479.1 ↗
30. Matsumoto, M. et al. Optimal uni-axial ferromagnetism in (la, ce) _2 fe 14 b for permanent magnets. arXivpreprint: http://arXiv.org/abs/arXiv:1901.10119 (2019).
31. Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Machine Learn. Res. 12, 2825–2830 (2011).
32. Head, T. et al. scikit-optimize/scikit-optimize: v0. 5.2. github.com/scikit-optimize/scikit-optimize (2018).
33. Sarracino, F. & Mikucka, M. Bias and efficiency loss in regression estimates due to duplicated observations: a monte carlo simulation. Survey Res. Methods 11, 17–44 (2017).
34. Sarkar, D., Bali, R. & Sharma, T. in A Problem-Solvers Guide To Building Real-World Intelligent Systems (Apress, Berkely, 2018).
35. Stoner, E. C. & Wohlfarth, E. A mechanism of magnetic hysteresis in heterogeneous alloys. Phil. Trans. R. Soc. Lond. A 240, 599–642 (1948).10.1098/rsta.1948.0007 ↗
36. Thielsch, J., Bittner, F. & Woodcock, T. G. Magnetization reversal processes in hot-extruded -MnAl-C. J. Magn. Magn. Mater. 426, 25–31 (2017).10.1016/j.jmmm.2016.11.045 ↗