Data-Driven Discovery of Composition-Dependent Constitutive Models for Hyperelasticity and Viscoelasticity of Digital Materials

The researchers proposed a data-driven framework for the construction of composite materials, aimed at addressing the complex behavior issues of digital materials in terms of stiffness, nonlinearity, and rate dependence. This framework is based on Bergström and Boyce formulas, retains the classical model structure, and uses multi-rate uniaxial compression data to predict intrinsic parameters across components or construct neural networks. Experimental verification shows that this method can effectively capture rate-dependent stiffness and hysteresis effects under different components, while maintaining thermodynamic consistency.