Fast Machine Learning for Science Conference 2026

Predicting grain-size-aware flow behavior via a physics-informed neural network elasto-viscoplastic model

Not scheduled

20m

Poster Reception & Poster Session

Speaker

Adnan Eghtesad

Description

We introduce a physics-informed elasto-viscoplastic (NN-EVP) framework that utilizes Input Convex Neural Networks (ICNNs) to ensure thermodynamic consistency while maintaining high predictive expressivity. Developed within the PyTorch ecosystem, this automated constitutive modeling tool is validated against both synthetic power-law data and experimental uniaxial deformation data under large plastic strains. The framework successfully discovers the Hall–Petch relationship, enabling accurate extrapolation across varying grain sizes. Finally, we demonstrate the model’s practical utility by integrating these discovered neural network laws into a finite element analysis (FEA) workflow for metallic alloys.