A micromechanics-based recurrent neural networks model for path-dependent cyclic deformation of short fiber composites
This work addresses the computationally expensive micromechanical modeling problem for materials scientists and engineers, offering an incremental improvement by integrating machine learning with existing methods.
The paper tackled the challenge of predicting path-dependent plastic behavior in short fiber composites by developing a recurrent deep neural network model trained on micromechanical simulations, achieving very accurate and computationally efficient predictions compared to independent simulations.
The macroscopic response of short fiber reinforced composites is dependent on an extensive range of microstructural parameters. Thus, micromechanical modeling of these materials is challenging and in some cases, computationally expensive. This is particularly important when path-dependent plastic behavior is needed to be predicted. A solution to this challenge is to enhance micromechanical solutions with machine learning techniques such as artificial neural networks. In this work, a recurrent deep neural network model is trained to predict the path-dependent elasto-plastic stress response of short fiber reinforced composites, given the microstructural parameters and the strain path. Micromechanical meanfield simulations are conducted to create a data base for training the validating the model. The model gives very accurate predictions in a computationally efficient manner when compared with independent micromechanical simulations.