.png){kind=icon}
.png){kind=icon}
Return
Learning inelastic constitutive models from stress–strain data under hard thermodynamic constraints
.png){kind=icon}
PRE
AI
F
DOI：10.1016/j.cma.2026.119260.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Non-equilibrium thermodynamics imposed as hard constraints. • Inelastic constitutive models identified from simple stress–strain data. • Learned models generalise to demanding loading paths beyond the training set. • Interpretable internal variables are identified. • Application to history-dependent granular media with high-fidelity, grain-scale simulations.
Keywords:
Machine learning
Data-driven constitutive modelling
Hard-constrained learning
Non-equilibrium thermodynamics
Transport equations
Granular materials
Journal
IF:
7.3
Papers:
1.3W
Citations:
5.6W
Organization
No organization information available
Cited Papers