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 (0.003% error). After 400 time steps, the accumulated error reaches 0.78 %. The computing time of each time step is 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.
Original language | English |
---|---|
Title of host publication | 2022 IEEE Design Methodologies Conference (DMC) |
Pages | 1-6 |
Number of pages | 6 |
DOIs | |
Publication status | Published - 2 Sept 2022 |
Event | 2022 IEEE Design Methodologies Conference (DMC) - Bath, United Kingdom Duration: 1 Sept 2022 → 2 Sept 2022 |
Conference
Conference | 2022 IEEE Design Methodologies Conference (DMC) |
---|---|
Period | 1/09/22 → 2/09/22 |
Keywords
- Geometry
- Solid modeling
- Three-dimensional displays
- Graph neural networks
- Mathematical models
- Real-time systems
- Behavioral sciences