Deep learning for plasticity and thermo-viscoplasticity

Predicting history-dependent materials' responses is crucial, as path-dependent behavior appears while characterizing or geometrically designing many materials (e.g., metallic and polymeric cellular materials), and it takes place in manufacturing and processing of many materials (e.g., metal solidification). Such phenomena can be computationally intensive and challenging when numerical schemes such as the finite element method are used. Here, we have applied a variety of sequence learning models to almost instantly predict the history-dependent responses (stresses and energy) of a class of cellular materials as well as the multiphysics problem of steel solidification with multiple thermo-viscoplasticity constitutive models accounting for substantial temperature, time, and path dependencies, and phase transformation. We have shown the gated recurrent unit (GRU) as well as the temporal convolutional network (TCN), can both accurately learn and almost instantly predict these irreversible, and historyand time-dependent phenomena, while TCN is more computationally efficient during the training process. This work may open the door for the broader adoption of data-driven models in similar computationally challenging constitutive models in plasticity and inelasticity.

Automated summary

This study applied sequence learning models to predict the history-dependent responses of materials, showing that gated recurrent unit and temporal convolutional network can accurately learn and instantly predict such phenomena, with TCN being more computationally efficient during the training process.