A micromechanics-based recurrent neural networks model for path-dependent cyclic deformation of short fiber composites

2022/09/27 by J. Friemann, B. Dashtbozorg, Friemann, J. +5 · 1 citation
Engineering · #Composite Material Mechanics #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Materials Science (cond-mat.mtrl-sci) #Mechanical Behavior of Composites #Neural and Evolutionary Computing (cs.NE) #Topology Optimization in Engineering

paper · pdf · doi:10.48550/arxiv.2210.00842

openalex publication_date 2022/09/27 · openalex created_date 2022/10/06 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• ViT-Transformer: Self-attention mechanism based constitutive modeling for nonlinear heterogeneous materials

Related

• Augmentation of scarce data -- a new approach for deep-learning modeling of composites
• Physically recurrent neural network for rate and path-dependent heterogeneous materials in a finite strain framework
• Physically Recurrent Neural Networks for Computational Homogenization of Composite Materials with Microscale Debonding
• Prediction of local elasto-plastic stress and strain fields in a two-phase composite microstructure using a deep convolutional neural network
• Test-time data augmentation: improving predictions of recurrent neural network models of composites