A Convex Route to Thermoelasticity: Learning Internal Energy and Dissipation
Researchers have developed a novel physics-based neural network framework for modeling thermomechanics, focusing on internal energy and dissipation potentials rather than traditional Helmholtz energy. This approach simplifies the incorporation of thermodynamic principles and ensures thermodynamic admissibility by construction. The framework utilizes input convex neural networks to represent internal energy and dissipation, embedding objectivity and material symmetry directly into the architecture. The system has demonstrated accurate performance on synthetic and experimental datasets for various materials and thermomechanical responses. AI
IMPACT This framework could advance the accuracy and efficiency of simulating material behavior in engineering applications.