Large Language Model-Enabled Constitutive Modeling for Rate-Dependent Plasticity and Automatic UMAT Subroutine Generation

In materials science and engineering design, high-fidelity and high-efficiency numerical simulation has become a driving force for innovation and practical implementation. To address longstanding bottlenecks in the development of conventional material constitutive models—such as lengthy modeling cycles and difficulties in numerical implementation—this study proposes an intelligent modeling and code generation approach powered by large language models. A structured knowledge base integrating constitutive theory, numerical algorithms, and UMAT (User Material) interface specifications is constructed, and a retrieval-augmented generation strategy is employed to establish an end-to-end workflow spanning experimental data parsing, constitutive model formulation, and automatic UMAT subroutine generation. Experimental results show that the method achieves high accuracy for both a classical Johnson–Cook model and a physics-informed neural network (PINN) model, with key parameter identification errors below 5%. Moreover, the automatically generated UMAT subroutines yield finite element simulation results in Abaqus that are highly consistent with theoretical predictions (coefficient of determination R2 > 0.98) while maintaining good numerical stability. This framework is currently focused on the automatic construction of rate-dependent elastoplastic material models, and its core method also provides a clear path for extending to other constitutive categories such as hyperelasticity and viscoelasticity. This work provides an effective technical route for the rapid development and reliable numerical implementation of material constitutive models, significantly advancing the intelligence level of computational mechanics research and improving engineering application efficiency.