FE${}^{\text{ANN}}$ $-$ An efficient data-driven multiscale approach based on physics-constrained neural networks and automated data mining

Abstract

Herein, we present a new data-driven multiscale framework called FE${}^{\text{ANN}}$ which is based on two main keystones: the usage of physics-constrained artificial neural networks (ANNs) as macroscopic surrogate models and an autonomous data mining process. Our approach allows the efficient simulation of materials with complex underlying microstructures which reveal an overall anisotropic and nonlinear behavior on the macroscale. Thereby, we restrict ourselves to finite strain hyperelasticity problems for now. By using a set of problem specific invariants as the input of the ANN and the Helmholtz free energy density as the output, several physical principles, e.g., objectivity, material symmetry, compatibility with the balance of angular momentum and thermodynamic consistency are fulfilled a priori. The necessary data for the training of the ANN-based surrogate model, i.e., macroscopic deformations and corresponding stresses, are collected via computational homogenization of representative volume elements (RVEs). Thereby, the core feature of the approach is given by a completely autonomous mining of the required data set within an overall loop. In each iteration of the loop, new data are generated by gathering the macroscopic deformation states from the macroscopic finite element (FE) simulation and a subsequently sorting by using the anisotropy class of the considered material. Finally, all unknown deformations are prescribed in the RVE simulation to get the corresponding stresses and thus to extend the data set. The proposed framework consequently allows to reduce the number of time-consuming microscale simulations to a minimum. It is exemplarily applied to several descriptive examples, where a fiber reinforced composite with a highly nonlinear Ogden-type behavior of the individual components is considered.

References in corpus (14)

• Polyconvex anisotropic hyperelasticity with neural networks
• Multiscale modeling of inelastic materials with Thermodynamics-based Artificial Neural Networks (TANN)
• NN-EUCLID: deep-learning hyperelasticity without stress data
• Data-driven fracture mechanics
• On physics-informed data-driven isotropic and anisotropic constitutive models through probabilistic machine learning and space-filling sampling
• Data-driven Tissue Mechanics with Polyconvex Neural Ordinary Differential Equations
• A hybrid approach to simulate the homogenized irreversible elastic-plastic deformations and damage of foams by neural networks
• Local approximate Gaussian process regression for data-driven constitutive laws: Development and comparison with neural networks
• Thermodynamically Consistent Machine-Learned Internal State Variable Approach for Data-Driven Modeling of Path-Dependent Materials
• Model-data-driven constitutive responses: application to a multiscale computational framework
• Learning hyperelastic anisotropy from data via a tensor basis neural network
• An efficient monolithic solution scheme for FE${}^2$ problems
• Finite electro-elasticity with physics-augmented neural networks
• On-the-fly adaptivity for nonlinear twoscale simulations using artificial neural networks and reduced order modeling

Cited by in corpus (13)

• Deep Learning in Deterministic Computational Mechanics
• A comparative study on different neural network architectures to model inelasticity
• Consistent machine learning for topology optimization with microstructure-dependent neural network material models
• Physics-augmented neural networks for constitutive modeling of hyperelastic geometrically exact beams
• Inverse design of spinodoid structures using Bayesian optimization
• When invariants matter: The role of I1 and I2 in neural network models of incompressible hyperelasticity
• A Complement to Neural Networks for Anisotropic Inelasticity at Finite Strains
• Magnetic elastomers as specific soft actuators -- predicting particular modes of deformation from selected configurations of magnetizable inclusions
• Precise, efficient and flexible modeling of crystallizing elastomers based on physics-augmented neural networks
• Assessment of hybrid machine learning models for non-linear system identification of fatigue test rigs
• Empirical Hyper Element Integration Method (EHEIM) with Unified Integration Criteria for Efficient Hyper Reduced FE${}^2$ Simulations
• A physics-augmented neural network framework for finite strain incompressible viscoelasticity
• Construction of minimal integrity basis for anisotropic hyperelasticity via structural tensors