A single Long Short-Term Memory network for enhancing the prediction of path-dependent plasticity with material heterogeneity and anisotropy
This work addresses material science challenges in modeling complex elastoplastic behaviors, but it is incremental as it applies an existing LSTM method to a new domain-specific problem.
The study tackled predicting path-dependent plasticity in materials with heterogeneity and anisotropy using a single LSTM network, achieving accurate capture of J2 plasticity responses under monotonic and arbitrary loading paths, including for transversely anisotropic materials with computational homogenization.
This study presents the applicability of conventional deep recurrent neural networks (RNN) to predict path-dependent plasticity associated with material heterogeneity and anisotropy. Although the architecture of RNN possesses inductive biases toward information over time, it is still challenging to learn the path-dependent material behavior as a function of the loading path considering the change from elastic to elastoplastic regimes. Our attempt is to develop a simple machine-learning-based model that can replicate elastoplastic behaviors considering material heterogeneity and anisotropy. The basic Long-Short Term Memory Unit (LSTM) is adopted for the modeling of plasticity in the two-dimensional space by enhancing the inductive bias toward the past information through manipulating input variables. Our results find that a single LSTM based model can capture the J2 plasticity responses under both monotonic and arbitrary loading paths provided the material heterogeneity. The proposed neural network architecture is then used to model elastoplastic responses of a two-dimensional transversely anisotropic material associated with computational homogenization (FE2). It is also found that a single LSTM model can be used to accurately and effectively capture the path-dependent responses of heterogeneous and anisotropic microstructures under arbitrary mechanical loading conditions.