Thermodynamics-based Artificial Neural Networks for constitutive modeling

Abstract

Machine Learning methods and, in particular, Artificial Neural Networks (ANNs) have demonstrated promising capabilities in material constitutive modeling. One of the main drawbacks of such approaches is the lack of a rigorous frame based on the laws of physics. This may render physically inconsistent the predictions of a trained network, which can be even dangerous for real applications. Here we propose a new class of data-driven, physics-based, neural networks for constitutive modeling of strain rate independent processes at the material point level, which we define as Thermodynamics-based Artificial Neural Networks (TANNs). The two basic principles of thermodynamics are encoded in the network's architecture by taking advantage of automatic differentiation to compute the numerical derivatives of a network with respect to its inputs. In this way, derivatives of the free-energy, the dissipation rate and their relation with the stress and internal state variables are hardwired in the network. Consequently, our network does not have to identify the underlying pattern of thermodynamic laws during training, reducing the need of large data-sets. Moreover the training is more efficient and robust, and the predictions more accurate. Finally and more important, the predictions remain thermodynamically consistent, even for unseen data. Based on these features, TANNs are a starting point for data-driven, physics-based constitutive modeling with neural networks. We demonstrate the wide applicability of TANNs for modeling elasto-plastic materials, with strain hardening and strain softening. Detailed comparisons show that the predictions of TANNs outperform those of standard ANNs. TANNs ' architecture is general, enabling applications to materials with different or more complex behavior, without any modification.

References in corpus (1)

• Learning Constitutive Relations using Symmetric Positive Definite Neural Networks

Cited by in corpus (55)

• Intelligent Computing: The Latest Advances, Challenges and Future
• A new family of Constitutive Artificial Neural Networks towards automated model discovery
• Multiscale modeling of inelastic materials with Thermodynamics-based Artificial Neural Networks (TANN)
• Automated discovery of generalized standard material models with EUCLID
• Deep Learning in Deterministic Computational Mechanics
• Recent Advances and Applications of Machine Learning in Experimental Solid Mechanics: A Review
• On physics-informed data-driven isotropic and anisotropic constitutive models through probabilistic machine learning and space-filling sampling
• FE${}^{\text{ANN}}$ $-$ An efficient data-driven multiscale approach based on physics-constrained neural networks and automated data mining
• A deep learning energy-based method for classical elastoplasticity
• Thermal Neural Networks: Lumped-Parameter Thermal Modeling With State-Space Machine Learning
• Theory and implementation of inelastic Constitutive Artificial Neural Networks
• Thermodynamically Consistent Machine-Learned Internal State Variable Approach for Data-Driven Modeling of Path-Dependent Materials
• 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
• Modular machine learning-based elastoplasticity: generalization in the context of limited data
• Recurrent Neural Networks (RNNs) with dimensionality reduction and break down in computational mechanics; application to multi-scale localization step
• Learning hyperelastic anisotropy from data via a tensor basis neural network
• Evolution TANN and the identification of internal variables and evolution equations in solid mechanics
• Finite electro-elasticity with physics-augmented neural networks
• Gibbs-Duhem-Informed Neural Networks for Binary Activity Coefficient Prediction
• Learning macroscopic internal variables and history dependence from microscopic models
• Learning nonlocal constitutive models with neural networks
• LS-DYNA Machine Learning-based Multiscale Method for Nonlinear Modeling of Short Fiber-Reinforced Composites
• Reduced and All-at-Once Approaches for Model Calibration and Discovery in Computational Solid Mechanics
• Thermodynamics-Consistent Graph Neural Networks
• Efficient Implementation of Non-linear Flow Law Using Neural Network into the Abaqus Explicit FEM code
• A machine learning-based viscoelastic-viscoplastic model for epoxy nanocomposites with moisture content
• Neural integration for constitutive equations using small data
• Learning constitutive models from microstructural simulations via a non-intrusive reduced basis method
• I-FENN for thermoelasticity based on physics-informed temporal convolutional network (PI-TCN)
• A Generative Modeling Framework for Inferring Families of Biomechanical Constitutive Laws in Data-Sparse Regimes
• Cooperative data-driven modeling
• I-FENN with Temporal Convolutional Networks: expediting the load-history analysis of non-local gradient damage propagation
• Automated Model Discovery for Tensional Homeostasis: Constitutive Machine Learning in Growth and Remodeling
• A generalized dual potential for inelastic Constitutive Artificial Neural Networks: A JAX implementation at finite strains
• A mixed formulation for physics-informed neural networks as a potential solver for engineering problems in heterogeneous domains: comparison with finite element method
• Recovering Mullins damage hyperelastic behaviour with physics augmented neural networks
• An equivariant neural operator for developing nonlocal tensorial constitutive models
• G2Φnet: Relating Genotype and Biomechanical Phenotype of Tissues with Deep Learning
• A Complement to Neural Networks for Anisotropic Inelasticity at Finite Strains
• Machine learning-based multiscale constitutive modelling: Development and application to dual-porosity mass transfer
• Symmetry-enforcing neural networks with applications to constitutive modeling
• Data-driven numerical site response
• Structure-preserving Sparse Identification of Nonlinear Dynamics for Data-driven Modeling
• Hybrid data-driven and physics-informed regularized learning of cyclic plasticity with Neural Networks
• Mesh d-refinement: a data-based computational framework to account for complex material response
• How machine learning can help the design and analysis of composite materials and structures?
• Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids
• Precise, efficient and flexible modeling of crystallizing elastomers based on physics-augmented neural networks
• A deep learning energy method for hyperelasticity and viscoelasticity
• Teaching Solid Mechanics to Artificial Intelligence: a fast solver for heterogeneous solids
• A physics-augmented neural network framework for finite strain incompressible viscoelasticity
• Learning inelastic constitutive models from stress-strain data under hard thermodynamic constraints
• Data-driven discovery of interpretable causal relations for deep learning material laws with uncertainty propagation
• Polar Interpolants for Thin-Shell Microstructure Homogenization