Approximating Steady-State Maxwell’s Equations via Physics-Informed Neural Networks

(welcome applications for the research internship positions in a form of Master thesis)

Supported by the Emerging Talents Initiative No. 5500168 (ETI) at Friedrich-Alexander-Universität Erlangen-Nürnberg.

Duration: 2022 – now

In recent years, Physics-Informed Neural Networks (PINNs) have started to arise frequently in many areas of science and engineering. PINNs are revolutionizing the way many physics-related problems are solved by combining classic Neural Networks explicitly with the underlying Physics of a certain problem.

This is a collaboration with Fraunhofer IISB, Erlangen.

People involved

Scope / Goal

In recent years, Physics-Informed Neural Networks (PINNs) have started to arise frequently in many areas of science and engineering. PINNs are revolutionizing the way many physics-related problems are solved by combining classic Neural Networks explicitly with the underlying Physics of a certain problem.

The intrinsic Machine-Learning (ML) nature of PINNs enables huge speed-ups for simulations at inference time (i.e., after training) while the introduced Physics ensure the conservation of the physical laws behind the problem.

We consider a Use-Case from Power-Electronics, more specifically the topology optimization of a ferrit core for a choke or coil, which requires accurate and fast prediction of magnetic flux and field intensity inside the system.

This task is tackled by:

• Deriving an adequate mathematical description based on the steady-state Maxwell Equations (2D symmetric) with corresponding Initial- and Boundary-Conditions [1].

• Enhancing frameworks such as Nvidia Modulus for reproducible training, evaluation and visualization of PINNs [2].

• Application of Hyperparameter-Tuning and other ML-Enhancing Techniques like Loss-Balancing for PINNs [3]. This Project is a collaboration with Fraunhofer IISB, Erlangen.


[1] J. Lima, D. Psaltis. MaxwellNet: Physics-driven deep neural network training based on Maxwell’s equations, https://aip.scitation.org/doi/pdf/10.1063/5.0071616

[2] A Framework for Developing Physics Machine Learning Neural Network Models, https://developer.nvidia.com/modulus

[3] Bischof et al., „Multi-Objective Loss Balancing for Physics-Informed Deep Learning“, 2110.09813.pdf (arxiv.org)


You might like

Date: Thu. May 19, 2022 Organized by: Durham University, Seminars in Mathematical Sciences Title: Optimal Control Design for Fluid Mixing: from Open-Loop to Closed-Loop Speaker: Visitor scientist Prof. Dr. Weiwei Hu Affiliation: University of Georgia (USA) Abstract. The question of what velocity fields effectively enhance or […]
Date: Wed. May 11, 2022 Organized by: FAU DCN-AvH, Chair for Dynamics, Control and Numerics – Alexander von Humboldt Professorship at FAU Erlangen-Nürnberg (Germany) Title: Some observations on the turnpike property and optimal actuator design Speaker: Dr. Borjan Geshkovski Affiliation: MIT – Massachusetts Institute of Technology […]
Date: July, 2022 Enrique Zuazua, 2022 W.T. and Idalia Reid Prize Laureate: Prof. Dr. Enrique Zuazua Affiliation: Friedrich-Alexander-Universität Erlangen-Nürnberg (Germany) Award: 2022 W.T. and Idalia Reid Prize By: SIAM – Society for Industrial and Applied Mathematics Location: SIAM Annual Meeting. Pittsburgh, Pennsylvania (USA) Born in Eibar “City of […]
© 2019-2022 FAU DCN-AvH Chair for Dynamics, Control and Numerics - Alexander von Humboldt Professorship at Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany | Imprint | Contact