Summary

Neural Networks as fast physics simulators have a large potential for many engineering design tasks. Prerequisites for a wide-spread application are an easy-to-use workflow for generating training datasets in a reasonable time, and the capability of the network to generalize to unseen systems. In contrast to most previous works where training systems are similar to the evaluation dataset, we propose to adapt the type of training system to the network architecture. Specifically, we apply a fully convolutional network and, thus, design 3D systems of randomly located voxels with randomly assigned physical properties. The idea is tested for the transient heat diffusion in electronic systems. Training only on random 'Minecraft' systems, we obtain good generalization to electronic systems four times as large as the training systems (one-step prediction error of 0.07 % vs 0.8 %).

Abstract

The PDF file did not load properly or your web browser does not support viewing PDF files. Download directly to your device: Download PDF document

Full Paper

The PDF file did not load properly or your web browser does not support viewing PDF files. Download directly to your device: Download PDF document
Back to Top
GET PDF

Document information

Published on 24/11/22
Accepted on 24/11/22
Submitted on 24/11/22

Volume Science Computing, 2022
DOI: 10.23967/eccomas.2022.054
Licence: CC BY-NC-SA license

Document Score

0

Views 2
Recommendations 0

Share this document

claim authorship

Are you one of the authors of this document?