HIGHLIGHTS
- who: Vasilis Krokos from the School of Engineering, Cardiff University, Cardiff, UK have published the research: A Bayesian multiscale CNN framework to predict local stress fields in structures with microscale features, in the Journal: (JOURNAL)
- what: The authors propose to replace the local microscale solution by an EncoderDecoder Convolutional Neural Network that will generate fine-scale stress corrections to coarse predictions around unresolved microscale features without prior parametrisation of local microscale problems. To circumvent this fundamental difficulty, the authors propose to convert the field of material properties into an image and use a convolutional neural_network . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.