Description
High-performance magnets play a key role in green technologies, including sustainable energy production and clean transport. In order to achieve the climate policy goal of two degrees, rapid electrification of the powertrain is required. Climate policy has a significant impact on the demand for critical materials. The average annual neodymium demand for energy technologies, cars and appliances is expected to increase eightfold between 2015 and 2050. Neodymium and heavy rare earth elements such as terbium and dysprosium are important for the operation of permanent magnets at high temperatures. To address the supply risk of rare-earth elements, magnets are being developed that can both eliminate the use of terbium and dysprosium and reduce the neodymium content. These goals require new strategies for materials design. There is a need to tune the materials composition, to control the grain structure, and to combine different materials at the device level. In this project we aim to develop machine learning methods that assist materials and device development by integrating physical models over all relevant length scales. Guidelines for magnet and device production will be computed taking into account the element supply and raw material costs. In this project a world-leading research group in computational magnetism and a global automotive manufacturer will work together. Excellent computational tools have been developed for the simulation of magnetic materials at various length scales. The applicant is author of micromagnetic software that treats magnetization processes on a mesoscopic level. His software is used world-wide by universities, research institutions, and companies for magnet data storage, magnetic sensors, and permanent magnetic materials design. At all length scale, the simulation of magnetic materials is resource intensive. The problem size is limited and simulations are time consuming. Therefore, numerical optimization that takes into account the material properties at the different length is hardly applied. Machine learning techniques can bridge the length scales. Once trained, machine learning models are fast and can be used for multiparameter optimization. A high magnetization and a high magnetocrystalline anisotropy are essential prerequisites for a permanent magnet material. We will create a machine learning model that maps chemical composition to magnetization and anisotropy, which are input parameters for micromagnetic simulations. Coercive fields of core-shell grains will be computed for various materials combinations and geometrical features on massively parallel hardware. We will train a gradient boost regressor that links geometry and rare-earth content to the coercive field of a single multiphase grain. The single grain model is the building block of a reduced order model for magnetization reversal that takes into account magnetic interactions between the grains of the magnet. A further speed-up for computing magnetization curves will be achieved by a neural network model for domain evolution in latent space. The domain evolution model will be tested by comparing simulation results with measured first order reversal curve diagrams. Coarse graining gives the effective permeability tensor to be used in a quasi-static Maxwell solver. At the macroscale a convolutional neural network model will be developed for fast magnetic field estimation. The optimization potential of the proposed methodology is two-fold: Multi-phase optimization gives the chemical compounds and geometry of a core-shell grain at the microscopic level. At the device level multi-material optimization assigns high coercive (and expensive) materials only to those regions that are subject to strong demagnetizing fields.
Details
Duration | 01/09/2020 - 31/08/2027 |
---|---|
Funding | Private (Stiftungen, Vereine etc.) |
Program |
|
Department | |
Principle investigator for the project (University for Continuing Education Krems) | Univ.-Doz.Dipl.-Ing.Dr. Thomas Schrefl |
Publications
Ali, Q.; Fischbacher, J.; Kovacs, A.; Özelt, H.; Gusenbauer, M.; Moustafa, H.; Böhm, D.; Breth, L.; Schrefl, T. (2024). Defect manipulation for the coercivity enhancement of Nd-Fe-B permanent magnets. Physica B: Condensed Matter, Vol. 678: 415759
Kovacs, A.; Fischbacher, J.; Oezelt, H.; Kornell, A.; Ali, Q.; Gusenbauer, M.; Yano, M.; Sakuma, N.; Kinoshita, A.; Shoji, T.; Kato, A.; Hong, Y.; Grenier, S.; Devillers, T.; Dempsey, N. M.; Fukushima, T.; Akai, H.; Kawashima, N.; Miyake, T.; Schrefl, T. (2023). Physics-Informed Machine Learning Combining Experiment and Simulation for the Design of Neodymium-Iron-Boron Permanent Magnets with Reduced Critical-Elements Content. Frontiers in Materials 2023, Vol. 9: 1-19
Okabe, R.; Li, M.; Iwasaki, Y.; Regnault N.; Felser, C.; Shirai, M.; Kovacs, A.; Schrefl, T.; Hirohata, A. (2023). Materials Informatics for the Development and Discovery of Future Magnetic Materials. IEEE Magnetics Letters, vol. 14: 1-5
Schaffer, S.; Schrefl, T.; Oezelt, H.; Kovacs, A.; Breth, L.; Mauser, N.J.; Suess, D.; Exl, L. (2023). Physics-informed machine learning and stray field computation with application to micromagnetic energy minimization. Journal of Magnetism and Magnetic Materials, 576: 170761
Ali, Q.; Fischbacher, J.; Kovacs, A.; Oezelt, H.; Gusenbauer, M.; Schrefl, T. (2023). Tuning the coercivity of permanent magnets by the combined effect of field angle and defect thickness. In: IEEE, proceedings in 2023 IEEE International Magnetic Conference - Short Papers (INTERMAG Short Papers): 1-2, IEEE, Sendai, Japan
Ali, Q.; Fischbacher, J.; Kovacs, A.; Oezelt, H.; Gusenbauer, M.; Yano, M.; Sakuma, N.; Kinoshita, A.; Shoji, T.; Kato, A.; Schrefl, T. (2023). Benchmarking for systematic coarse-grained micromagnetics. In: HMM, proceedings in 13th International Symposium on Hysteresis Modeling and Micromagnetics (HMM 2023): 1, HMM, WIen
Wager, C.; Kovacs, A.; Schrefl, T. (2023). Active Learning Scheme vs Conventional Optimization - developing a Python Framework. In: HMM, proceedings in 13th International Symposium on Hysteresis Modeling and Micromagnetics (HMM 2023): 1, HMM, Wien
Ali, Q.; Fischbacher, J.; Kovacs, A.; Oezelt, H.; Gusenbauer, M.; Moustafa, H.; Böhm, D.; Breth, L.; Schrefl, T. (2023). Defect Manipulation for the Coercivity Enhancement of Nd-Fe-B Permanent Magnets. SSRN, 2023: 4628986, Elesevier
Breth, L.; Fischbacher, J.; Kovacs, A.; Oezelt, H.; Schrefl, T.; Czettl, C.; Kuehrer, S.; Pachlhofer, J.; Schwarz, M.; Weirather, T.; Brueckl, H. (2023). Structural and micromagnetic modeling of the magnetic binder phase in WC-Co cemented carbides. IEEE International Magnetic Conference - Short Papers, 2023: https://doi.org/10.1109/INTERMAGShortPapers58606.2023.10304872
Heistracher, P.; Abert, C.; Bruckner, F.; Schrefl, T.; Suess, D. (2022). Proposal for a micromagnetic standard problem: domain wall pinning at phase boundaries. Journal of Magnetism and Magnetic Materials, Vol. 548: 168875
Kovacs, A.; Exl, L.; Kornell, A.; Fischbacher, J.; Hovorka, M.; Gusenbauer, M.; Breth, L.; Oezelt, H.; Yano, M.; Sakuma, N.; Kinoshita, A.; Shoji, T.; Kato, A.; Schrefl, T. (2022). Conditional physics informed neural networks. Communications in Nonlinear Science and Numerical Simulation, Vol. 104: 106041
Kovacs, A.; Exlc, L.; Kornell, A.; Fischbacher, J.; Hovorka, M.; Gusenbauer, M.; Breth, L.; Oezelt, H.; Praetorius, D.; Suess, D.; Schrefl, T. (2022). Magnetostatics and micromagnetics with physics informed neural networks. Journal of Magnetism and Magnetic Materials, Vol. 548: 168951
Mohapatra, J.; Fischbacher, J.; Gusenbauer, M.; Xing, M. Y.; Elkins, J.; Schrefl, T.; Liu, J. P. (2022). Coercivity limits in nanoscale ferromagnets. Phys. Rev. B, Vol. 105, Iss. 21: 214431
Oezelt, H.; Qu, L.; Kovacs, A.; Fischbacher, J.; Gusenbauer, M.; Beigelbeck, R.; Praetorius, D.; Yano, M.; Shoji, T.; Kato, A.; Chantrell, R.; Winklhofer, M.; Zimanyi, G.; Schrefl, T. (2022). Full- Spin-Wave-Scaled Stochastic Micromagnetism for Mesh-Independent Simulations of Ferromagnetic Resonance and Reversal. npj Computational Materials, Vol. 8: 35
Exl, L.; Mauser, N. J.; Schaffer, S.; Schrefl, T.; Suess, D.; (2021). Prediction of magnetization dynamics in a reduced dimensional feature space setting utilizing a low-rank kernel method. JOURNAL OF COMPUTATIONAL PHYSICS, 444: 110586
Lectures
MATERIALS INFORMATICS FOR PERMANENT MAGNET DESIGN
The 4th DXMaG Seminar, 06/12/2023
Materials informatics for permanent magnet design
Materials Innovation Strategy Symposium 2023, 05/12/2023
Modelling Magnets: From Atoms to Bulk Properties
Biomagnetic Sensing Seminar, 16/11/2023
Spotting the next big idea
68th Annual Conference on Magnetism and Magnetic Materials, 02/11/2023
Talking about magnets – information retrieval with large language models
68th Annual Conference on Magnetism and Magnetic Materials, 31/10/2023
Active Learning Scheme vs Conventional Optimization - developing a Python Framework
13th International Symposium on Hysteresis Modeling and Micromagnetics (HMM 2023), 05/06/2023
Benchmarking for systematic coarse-grained micromagnetics
13th International Symposium on Hysteresis Modeling and Micromagnetics (HMM 2023), 05/06/2023
Tuning the coercivity of permanent magnets by the combined effect of field angle and defect thickness
IEEE International Magnetics Conference INTERMAG 2023, 19/05/2023
Physics Informed Machine Learning for Permanent Magnet Design
IEEE International Magnetics Conference INTERMAG 2023, 18/05/2023
Magnetic Hardening of Neodymium-lean Permanent Magnets by Local Replacement of Grains by High Anisotropy Phases
Intermag 2023, 16/05/2023
Generative deep learning for permanent magnet microstructures
67th Annual Conference on Magnetism and Magnetic Materials (MMM 2022), 03/11/2022
Reduced Order Model for Large Multigrain Systems
67th Annual Conference on Magnetism and Magnetic Materials (MMM 2022), 03/11/2022
From chemical composition and temperature to micromagnetic anisotropy and vice-versa
67th Annual Conference on Magnetism and Magnetic Materials (MMM 2022), 02/11/2022
Materials Informatics for the Design of Rare-Earth Reduced Permanent Magnets
Magnetic Materials and Applications 22, 26/10/2022
Description of collective magnetization processes with machine learning models
CMAM 2022, 31/08/2022
Machine Learning Analysis of Multiphase Magnetic Microstructures
CIMTEC 2022, 23/06/2022
Physics informed neural networks for computational magnetism
MMM-Intermag 2022, 10/01/2022
Inverse design of Nd-substituted permanent magnets
Physics and the green economy, 25/11/2021
Machine learning, micromagnetics and magnet design
University of York, Computational Magnetism, 02/12/2020