Data-Driven On/Off Topology Optimization of Electromagnetic Devices Based on Graph Physics-Informed Neural Networks and Physics-Guided Reinforcement Learning
- 1National Center for Applied Mathematics in Chongqing, Chongqing Normal University, Chongqing 401331, China
Abstract
Topology optimization of electromagnetic devices is computationally formidable owing to the combinatorial on/off material distribution on unstructured finite element meshes and repeated Maxwell equation solves. This paper develops GPRL-TO, a data-driven framework addressing both difficulties through three synergistic components. First, a graph physics-informed neural network (G-PINN) reformulates the finite element mesh as a graph and predicts element-wise magnetic flux densities under embedded magnetoquasistatic constraints, with two to three orders of magnitude speedup over finite element analysis. Second, as the central methodological contribution, a physics residual-driven curiosity mechanism converts the Maxwell residual into an intrinsic reward of a reinforcement learning agent, steering exploration toward physically unreliable design regions; the residual also indicates surrogate reliability. Third, a Gumbel–Softmax relaxation with temperature annealing renders the binary design variables differentiable, so the discrete on/off decisions relax to a continuous reparameterization driven by energy-type design sensitivities evaluated on the surrogate-predicted fields, instead of adjoint solves. A layered bridge-prescribed refinement fixes an iron skeleton that closes the magnetic circuit and guarantees manufacturable multi-layer barriers by construction. On a synchronous reluctance motor rotor, the G-PINN attains a relative L2 error of 9.51%, and the layered optimization improves the objective by 16.7% while raising the saliency difference from essentially zero to +0.017165.
Related
- Efficient Joint Trajectory Optimization and Resource Allocation for Secure UAV Networks: A Deep Reinforcement Learning Approach
- Feature tracking in physics-informed neural networks via joint optimization of nonlinear deformation manifolds: application to shocks
- Adaptive Task Offloading Under Dynamic Topology via Graph Attention-Enhanced Reinforcement Learning for Layered UAV-Enabled Digital Twin Channel Modeling
- Reachability-Informed Reinforcement Learning for Multi-Impulse Interplanetary Transfers
- A new algorithm for topology optimization using a level-set method
BibTeX
@article{liu2026datadriven,
title = {{Data-Driven On/Off Topology Optimization of Electromagnetic Devices Based on Graph Physics-Informed Neural Networks and Physics-Guided Reinforcement Learning}},
author = {Xiaoyu Liu and Yihan Si and Wei Xiang and Mengxin Yang},
journal = {Mathematics},
year = {2026},
month = oct,
doi = {10.3390/math14203649},
url = {https://www.mdpi.com/2227-7390/14/20/3649},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Data-Driven On/Off Topology Optimization of Electromagnetic Devices Based on Graph Physics-Informed Neural Networks and Physics-Guided Reinforcement Learning
AU - Xiaoyu Liu
AU - Yihan Si
AU - Wei Xiang
AU - Mengxin Yang
PY - 2026
DA - 2026/10/09
JO - Mathematics
DO - 10.3390/math14203649
UR - https://www.mdpi.com/2227-7390/14/20/3649
AB - Topology optimization of electromagnetic devices is computationally formidable owing to the combinatorial on/off material distribution on unstructured finite element meshes and repeated Maxwell equation solves. This paper develops GPRL-TO, a data-driven framework addressing both difficulties through three synergistic components. First, a graph physics-informed neural network (G-PINN) reformulates the finite element mesh as a graph and predicts element-wise magnetic flux densities under embedded magnetoquasistatic constraints, with two to three orders of magnitude speedup over finite element analysis. Second, as the central methodological contribution, a physics residual-driven curiosity mechanism converts the Maxwell residual into an intrinsic reward of a reinforcement learning agent, steering exploration toward physically unreliable design regions; the residual also indicates surrogate reliability. Third, a Gumbel–Softmax relaxation with temperature annealing renders the binary design variables differentiable, so the discrete on/off decisions relax to a continuous reparameterization driven by energy-type design sensitivities evaluated on the surrogate-predicted fields, instead of adjoint solves. A layered bridge-prescribed refinement fixes an iron skeleton that closes the magnetic circuit and guarantees manufacturable multi-layer barriers by construction. On a synchronous reluctance motor rotor, the G-PINN attains a relative L2 error of 9.51%, and the layered optimization improves the objective by 16.7% while raising the saliency difference from essentially zero to +0.017165.
SN - 2227-7390
ER -