English

Towards Real Time Thermal Simulations for Design Optimization using Graph Neural Networks

Computational Engineering, Finance, and Science 2022-09-29 v1 Machine Learning Systems and Control Systems and Control Computational Physics

Abstract

This paper presents a method to simulate the thermal behavior of 3D systems using a graph neural network. The method discussed achieves a significant speed-up with respect to a traditional finite-element simulation. The graph neural network is trained on a diverse dataset of 3D CAD designs and the corresponding finite-element simulations, representative of the different geometries, material properties and losses that appear in the design of electronic systems. We present for the transient thermal behavior of a test system. The accuracy of the network result for one-step predictions is remarkable (\SI{0.003}{\%} error). After 400 time steps, the accumulated error reaches \SI{0.78}{\%}. The computing time of each time step is \SI{50}{ms}. Reducing the accumulated error is the current focus of our work. In the future, a tool such as the one we are presenting could provide nearly instantaneous approximations of the thermal behavior of a system that can be used for design optimization.

Keywords

Cite

@article{arxiv.2209.13348,
  title  = {Towards Real Time Thermal Simulations for Design Optimization using Graph Neural Networks},
  author = {Helios Sanchis-Alepuz and Monika Stipsitz},
  journal= {arXiv preprint arXiv:2209.13348},
  year   = {2022}
}

Comments

Presented at the Design Methodologies Conference 2022 (DMC2022) in Bath, England. 6 pages, 7 figures

R2 v1 2026-06-28T02:11:36.829Z