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

2022/09/21 by Sanchis-Alepuz, Helios, Stipsitz, Monika
#Computational Engineering #Computational Physics (physics.comp-ph) #FOS: Computer and information sciences #FOS: Electrical engineering #FOS: Physical sciences #Finance #Machine Learning (cs.LG) #Systems and Control (eess.SY) #and Science (cs.CE) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2209.13348

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 (\SI0.003% error). After 400 time steps, the accumulated error reaches \SI0.78%. The computing time of each time step is \SI50ms. 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.

Related

• DeepOHeat: Operator Learning-based Ultra-fast Thermal Simulation in 3D-IC Design
• Advancing Fluid-Based Thermal Management Systems Design: Leveraging Graph Neural Networks for Graph Regression and Efficient Enumeration Reduction
• A comprehensive comparison of neural operators for 3D industry-scale engineering designs
• Graph Neural Network-based Surrogate Models for Finite Element Analysis
• DeepOHeat-v1: Efficient Operator Learning for Fast and Trustworthy Thermal Simulation and Optimization in 3D-IC Design