Physics

AI extracts interpretable constitutive laws directly from solid-mechanics data

How the science connects

Machine learningSolid mechanicsConstitutive equat…

AI Insight

Researchers at the Eastern Institute of Technology in Ningbo have developed a graph-based artificial intelligence method that automatically extracts constitutive equations directly from experimental data of solid materials. The approach was successfully tested on alloy steels, lithium metal, and filled rubbers, demonstrating higher predictive accuracy than traditional empirical models while maintaining explicit, interpretable mathematical formulations. The study was published in Science Advances.


This method could significantly accelerate materials science research by automating the discovery of mathematical relationships that describe how materials deform and behave under stress. The approach eliminates much of the trial-and-error involved in developing constitutive models, potentially speeding up the design and optimization of new materials for engineering applications.


Understand the Science

Machine learning 236 articles Explore Concept → Solid mechanics Concept coming soon Constitutive equations Concept coming soon

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 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.

Source: AI extracts interpretable constitutive laws directly from solid-mechanics data