Recurrent neural networks and transfer learning for elasto-plasticity in woven composites
arXiv:2311.13434 · doi:10.1016/j.euromechsol.2024.105378
Abstract
As a surrogate for computationally intensive meso-scale simulation of woven composites, this article presents Recurrent Neural Network (RNN) models. Leveraging the power of transfer learning, the initialization challenges and sparse data issues inherent in cyclic shear strain loads are addressed in the RNN models. A mean-field model generates a comprehensive data set representing elasto-plastic behavior. In simulations, arbitrary six-dimensional strain histories are used to predict stresses under random walking as the source task and cyclic loading conditions as the target task. Incorporating sub-scale properties enhances RNN versatility. In order to achieve accurate predictions, the model uses a grid search method to tune network architecture and hyper-parameter configurations. The results of this study demonstrate that transfer learning can be used to effectively adapt the RNN to varying strain conditions, which establishes its potential as a useful tool for modeling path-dependent responses in woven composites.
arXiv commentThere are 25 pages and 13 EPS images. The paper includes links to supporting materials
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- Sequence to Sequence Learning with Neural Networks
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- A Critical Review of Recurrent Neural Networks for Sequence Learning
- Listen, Attend and Spell
- A machine learning based plasticity model using proper orthogonal decomposition
- Physically recurrent neural networks for path-dependent heterogeneous materials: embedding constitutive models in a data-driven surrogate
- A comparative study on different neural network architectures to model inelasticity
- Recurrent Neural Networks (RNNs) with dimensionality reduction and break down in computational mechanics; application to multi-scale localization step
- On-the-fly construction of surrogate constitutive models for concurrent multiscale mechanical analysis through probabilistic machine learning
- Geometric deep learning for computational mechanics Part II: Graph embedding for interpretable multiscale plasticity
- Cooperative data-driven modeling