AI RESEARCH
Discovering Thermodynamically Admissible Dissipation Potentials via Grammar-Based Symbolic Regression
arXiv CS.LG
•
ArXi:2605.31532v1 Announce Type: cross Constitutive laws for inelastic materials must satisfy strict thermodynamic admissibility requirements, yet current data-driven approaches sacrifice interpretability, even when formal guarantees are provided by physics-encoded architectures. We propose a symbolic regression framework for the data-driven discovery of dissipation potentials governing the evolution of internal variables within the Generalized Standard Materials (GSM) formalism.