English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Neural Networks as fast physics simulators have a large potential for manyengineering design tasks. Prerequisites for a wide-spread application are aneasy-to-use workflow for generating training datasets in a reasonable time, andthe capability of the network to generalize to unseen systems. In contrast tomost previous works where training systems are similar to the evaluationdataset, we propose to adapt the type of training system to the networkarchitecture. Specifically, we apply a fully convolutional network and, thus,design 3D systems of randomly located voxels with randomly assigned physicalproperties. The idea is tested for the transient heat diffusion in electronicsystems. Training only on random "Minecraft" systems, we obtain goodgeneralization to electronic systems four times as large as the trainingsystems (one-step prediction error of 0.07% vs 0.8%).

Approximating the full-field temperature evolution in 3D electronic systems from randomized "Minecraft" systems