Temperature-Aware Recurrent Neural Operator for Temperature-Dependent Anisotropic Plasticity in HCP Materials
This work addresses the problem of inefficient and inaccurate surrogate models for complex material behavior in computational mechanics, offering a domain-specific improvement for researchers and engineers in materials science.
The paper tackled the limitations of existing neural network surrogates for plasticity, such as poor extrapolation and inefficiency, by introducing the Temperature-Aware Recurrent Neural Operator (TRNO) for modeling temperature-dependent anisotropic plasticity in materials like magnesium, achieving high accuracy and a speedup of at least three orders of magnitude in multiscale simulations.
Neural network surrogate models for constitutive laws in computational mechanics have been in use for some time. In plasticity, these models often rely on gated recurrent units (GRUs) or long short-term memory (LSTM) cells, which excel at capturing path-dependent phenomena. However, they suffer from long training times and time-resolution-dependent predictions that extrapolate poorly. Moreover, most existing surrogates for macro- or mesoscopic plasticity handle only relatively simple material behavior. To overcome these limitations, we introduce the Temperature-Aware Recurrent Neural Operator (TRNO), a time-resolution-independent neural architecture. We apply the TRNO to model the temperature-dependent plastic response of polycrystalline magnesium, which shows strong plastic anisotropy and thermal sensitivity. The TRNO achieves high predictive accuracy and generalizes effectively across diverse loading cases, temperatures, and time resolutions. It also outperforms conventional GRU and LSTM models in training efficiency and predictive performance. Finally, we demonstrate multiscale simulations with the TRNO, yielding a speedup of at least three orders of magnitude over traditional constitutive models.