Physically recurrent neural networks for path-dependent heterogeneous materials: embedding constitutive models in a data-driven surrogate

Abstract

Driven by the need to accelerate numerical simulations, the use of machine learning techniques is rapidly growing in the field of computational solid mechanics. Their application is especially advantageous in concurrent multiscale finite element analysis (FE${}^2$) due to the exceedingly high computational costs often associated with it and the high number of similar micromechanical analyses involved. To tackle the issue, using surrogate models to approximate the microscopic behavior and accelerate the simulations is a promising and increasingly popular strategy. However, several challenges related to their data-driven nature compromise the reliability of surrogate models in material modeling. The alternative explored in this work is to reintroduce some of the physics-based knowledge of classical constitutive modeling into a neural network by employing the actual material models used in the full-order micromodel to introduce non-linearity. Thus, path-dependency arises naturally since every material model in the layer keeps track of its own internal variables. For the numerical examples, a composite Representative Volume Element with elastic fibers and elasto-plastic matrix material is used as the microscopic model. The network is tested in a series of challenging scenarios and its performance is compared to that of a state-of-the-art Recurrent Neural Network (RNN). A remarkable outcome of the novel framework is the ability to naturally predict unloading/reloading behavior without ever seeing it during training, a stark contrast with popular but data-hungry models such as RNNs. Finally, the proposed network is applied to FE${}^2$ examples to assess its robustness for application in nonlinear finite element analysis.

30 pages, 24 figures

References in corpus (7)

• Multiscale modeling of inelastic materials with Thermodynamics-based Artificial Neural Networks (TANN)
• Model-data-driven constitutive responses: application to a multiscale computational framework
• On-the-fly construction of surrogate constitutive models for concurrent multiscale mechanical analysis through probabilistic machine learning
• Physics-informed neural networks for modeling rate- and temperature-dependent plasticity
• Learning constitutive models from microstructural simulations via a non-intrusive reduced basis method
• Neural-network acceleration of projection-based model-order-reduction for finite plasticity: Application to RVEs
• Explainable artificial intelligence for mechanics: physics-informing neural networks for constitutive models

Cited by in corpus (4)

• Recurrent neural networks and transfer learning for elasto-plasticity in woven composites
• Multiscale Analysis of Woven Composites Using Hierarchical Physically Recurrent Neural Networks
• A viscoplasticity model with an invariant-based non-Newtonian flow rule for unidirectional thermoplastic composites
• Design of a specimen to train path-dependent deep learning material models from a single uniaxial test: eliciting strain diversity via automatically differentiable elastoplastic topology optimization