Physics aware machine learning for micromagnetic energy minimization: recent algorithmic developments

TL;DR

This paper advances machine learning techniques for 3D micromagnetic energy minimization by reformulating bounds, employing constrained neural networks, and demonstrating competitive accuracy and scalability over traditional methods.

Contribution

It introduces a novel approach combining Brown's energy bounds with mesh-free neural networks and constrained optimization for efficient micromagnetic simulations.

Findings

Mesh-free PINNs and ELMs achieve high accuracy in magnetostatic field computation.

The method scales efficiently to large and complex geometries.

Competitive performance with traditional numerical approaches in energy minimization.

Abstract

In this work, we explore advanced machine learning techniques for minimizing Gibbs free energy in full 3D micromagnetic simulations. Building on Brown's bounds for magnetostatic self-energy, we revisit their application in the context of variational formulations of the transmission problems for the scalar and vector potential. To overcome the computational challenges posed by whole-space integrals, we reformulate these bounds on a finite domain, making the method more efficient and scalable for numerical simulation. Our approach utilizes an alternating optimization scheme for joint minimization of Brown's energy bounds and the Gibbs free energy. The Cayley transform is employed to rigorously enforce the unit norm constraint, while R-functions are used to impose essential boundary conditions in the computation of magnetostatic fields. Our results highlight the potential of mesh-free Physics-Informed Neural Networks (PINNs) and Extreme Learning Machines (ELMs) when integrated with hard constraints, providing highly accurate approximations. These methods exhibit competitive performance compared to traditional numerical approaches, showing significant promise in computing magnetostatic fields and the application for energy minimization, such as the computation of hysteresis curves. This work opens the path for future directions of research on more complex geometries, such as grain structure models, and the application to large scale problem settings which are intractable with traditional numerical methods.