73 citations · 148 across the 7 of their papers we have counts for
7 papers
Graph Neural Networks to Predict Coercivity of Hard Magnetic Microstructures
Heisam Moustafa, Alexander Kovacs, Johann Fischbacher +5
Graph neural networks (GNN) are a promising tool to predict magnetic properties of large multi-grain structures, which can speed up the search for rare-earth free permanent magnets…
Physics-informed machine learning and stray field computation with application to micromagnetic energy minimization
Sebastian Schaffer, Thomas Schrefl, Harald Oezelt +5
We study the full 3d static micromagnetic equations via a physics-informed neural network (PINN) ansatz for the continuous magnetization configuration. PINNs are inherently mesh-fr…
FORC Diagram Features of Co Particles due to Reversal by Domain Nucleation
Leoni Breth, Johann Fischbacher, Alexander Kovacs +7
First Order Reversal Curve (FORC) diagrams are a popular tool in geophysics and materials science for the characterization of magnetic particles of natural and synthetic origin. Ho…
Description of collective magnetization processes with machine learning models
Alexander Kornell, Lukas Exl, Leoni Breth +11
This work introduces a latent space method to calculate the demagnetization reversal process of multigrain permanent magnets. The algorithm consists of two deep learning models bas…
Exploring the hysteresis properties of nanocrystalline permanent magnets using deep learning
Alexander Kovacs, Lukas Exl, Alexander Kornell +11
We demonstrate the use of model order reduction and neural networks for estimating the hysteresis properties of nanocrystalline permanent magnets from microstructure. With a data-d…
Magnetostatics and micromagnetics with physics informed neural networks
Alexander Kovacs, Lukas Exl, Alexander Kornell +8
Partial differential equations and variational problems can be solved with physics informed neural networks (PINNs). The unknown field is approximated with neural networks. Minimiz…
Conditional physics informed neural networks
Alexander Kovacs, Lukas Exl, Alexander Kornell +11
We introduce conditional PINNs (physics informed neural networks) for estimating the solution of classes of eigenvalue problems. The concept of PINNs is expanded to learn not only…