Work

Plasticity encoding and mapping during elementary loading for accelerated mechanical properties prediction

Year: 2025

Type: article

Abstract: Encoding metal plasticity captured from high-resolution digital image correlation (HR-DIC) is leveraged to predict a wide range of monotonic and cyclic macroscopic properties of metallic materials. To capture the spatial heterogeneity of plasticity that develops in metals, latent space features describing plasticity of small regions are spatially mapped across large fields. These latent space feature maps capture the complexity and heterogeneity of metal plasticity as a low-dimensional representation. These feature maps are then used to train a convolutional neural network-based model to predict monotonic and cyclic macroscopic properties. The approach is demonstrated on a large set of face-centered cubic metals, enabling rapid and accurate property prediction.

Source: Scripta Materialia

DOI: 10.1016/j.scriptamat.2025.117082

Authors: Mathieu Calvat, Chris Bean, Dhruv Anjaria, Haoren Wang, Kenneth Vecchio, J.C. Stinville

Institutions: University of Illinois Urbana-Champaign, University of California San Diego

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $3,220

Funders: National Science Foundation, Defense Advanced Research Projects Agency