Deep Learning Sequence Methods in Multiphysics Modeling of Steel Solidification

The solidifying steel follows highly nonlinear thermo-mechanical behavior depending on the loading history, temperature, and metallurgical phase fraction calculations (liquid, ferrite, austenite). Numerical modeling with a computationally challenging multiphysics approach is used high-performance computing to generate sufficient training testing data for subsequent deep learning. We have demonstrated how innovative sequence learning methods can learn from of slice traveling in continuous caster correctly instantly capture complex history temperature-dependent phenomenon test samples never seen by networks.