M. Stipsitz, H. Sanchis-Alepuz
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 %).
Keywords:
Published on 24/11/22Accepted on 24/11/22Submitted on 24/11/22
Volume Science Computing, 2022DOI: 10.23967/eccomas.2022.054Licence: CC BY-NC-SA license
Views 4Recommendations 0
Are you one of the authors of this document?