Effects of size and texture on anisotropic elasto-plasticity in Cu–Nb nanolaminates by integrating semi-empirical and data-driven approaches

Nanolaminated metallic materials exhibit exceptional combinations of mechanical strength, electrical conductivity, thermal stability, and radiation tolerance, making them attractive for demanding aerospace, nuclear, and microelectronic applications. These multilayered architectures are commonly fabricated using severe plastic deformation routes such as accumulative roll bonding (ARB), which progressively refines the individual layer thickness and makes interfacial structures. In this work, copper–niobium (Cu–Nb) nanolaminates are adopted as a representative model system to investigate texture evolution and size-dependent mechanical behavior across a wide range of layer thicknesses, from micrometer to nanometer scales. To model texture evolution, a deep learning approach based on artificial neural networks is employed, using predicted Euler angles as input for subsequent crystal plasticity finite element modeling (CPFEM). Finite element simulations are performed on a representative volume element (RVE) with periodic boundary conditions to accurately replicate the experimentally observed anisotropic elasto-plastic response in both rolling and transverse directions. The critical resolved shear stress is quantitatively linked to layer thickness via a data-driven deep symbolic regression approach, which reveals strong agreement with the classical Hall–Petch relationship. To further enhance computational efficiency, a recently developed mean-field β-model is integrated, achieving an order-of-magnitude reduction in computational cost compared to full-field CPFEM-RVE simulations. This semi-empirical and data-driven integrated approach not only provides an accurate predictive framework for the anisotropic mechanical behavior of nanolaminates but also offers valuable insights into layer size effects, texture evolution, and microstructure property relationships essential for the rational design of high-performance multilayered material.