AI extracts interpretable constitutive laws directly from solid-mechanics data
Researchers at the Eastern Institute of Technology (EIT), Ningbo, have developed a graph-based approach that directly extracts concise, accurate constitutive equations from solid-material experimental data.
Researchers at the Eastern Institute of Technology (EIT), Ningbo, have developed a graph-based approach that directly extracts concise, accurate constitutive equations from solid-material experimental data.
The short version
- The study, published in Science Advances, describes a method for discovering constitutive models for alloy steels, lithium metal and filled rubbers.
- It outperforms mainstream empirical models in predictive accuracy while preserving explicit, physically interpretable mathematical formulations.
- This article has been reviewed according to Science X's editorial process and policies .
What happened
The framework iteratively generates, evaluates and optimizes candidate graph-structured equations to produce physically consistent, mathematically compact and human-interpretable constitutive laws with high prediction fidelity. The research team validated the generality and superiority of GraphED on multiple solid-material systems with distinct mechanical characteristics.
Why it matters
For alloy steels, the method successfully discovered explicit equations governing strain-rate dependence and strain-hardening behaviors.
Summary by Nerd News Network. Read the full article at Phys.org via the links above and below.