NN-EUCLID: deep-learning hyperelasticity without stress data

Abstract

We propose a new approach for unsupervised learning of hyperelastic constitutive laws with physics-consistent deep neural networks. In contrast to supervised learning, which assumes the availability of stress-strain pairs, the approach only uses realistically measurable full-field displacement and global reaction force data, thus it lies within the scope of our recent framework for Efficient Unsupervised Constitutive Law Identification and Discovery (EUCLID) and we denote it as NN-EUCLID. The absence of stress labels is compensated for by leveraging a physics-motivated loss function based on the conservation of linear momentum to guide the learning process. The constitutive model is based on input-convex neural networks, which are capable of learning a function that is convex with respect to its inputs. By employing a specially designed neural network architecture, multiple physical and thermodynamic constraints for hyperelastic constitutive laws, such as material frame indifference, (poly-)convexity, and stress-free reference configuration are automatically satisfied. We demonstrate the ability of the approach to accurately learn several hidden isotropic and anisotropic hyperelastic constitutive laws - including e.g., Mooney-Rivlin, Arruda-Boyce, Ogden, and Holzapfel models - without using stress data. For anisotropic hyperelasticity, the unknown anisotropic fiber directions are automatically discovered jointly with the constitutive model. The neural network-based constitutive models show good generalization capability beyond the strain states observed during training and are readily deployable in a general finite element framework for simulating complex mechanical boundary value problems with good accuracy.

31 pages, 17 figures

References in corpus (5)

• Data-driven fracture mechanics
• Discovering plasticity models without stress data
• Variational Onsager Neural Networks (VONNs): A thermodynamics-based variational learning strategy for non-equilibrium PDEs
• On-the-fly construction of surrogate constitutive models for concurrent multiscale mechanical analysis through probabilistic machine learning
• Full-field stress computation from measured deformation fields: a hyperbolic formulation

Cited by in corpus (37)

• A new family of Constitutive Artificial Neural Networks towards automated model discovery
• Neural networks meet hyperelasticity: A guide to enforcing physics
• Automated discovery of generalized standard material models with EUCLID
• Deep Learning in Deterministic Computational Mechanics
• FE${}^{\text{ANN}}$ $-$ An efficient data-driven multiscale approach based on physics-constrained neural networks and automated data mining
• Finite electro-elasticity with physics-augmented neural networks
• Automated identification of linear viscoelastic constitutive laws with EUCLID
• Automated discovery of interpretable hyperelastic material models for human brain tissue with EUCLID
• Data-driven anisotropic finite viscoelasticity using neural ordinary differential equations
• MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations
• Reduced and All-at-Once Approaches for Model Calibration and Discovery in Computational Solid Mechanics
• Can KAN CANs? Input-convex Kolmogorov-Arnold Networks (KANs) as hyperelastic constitutive artificial neural networks (CANs)
• Physics-Informed Neural Network-Based Discovery of Hyperelastic Constitutive Models from Extremely Scarce Data
• HyperCAN: Hypernetwork-Driven Deep Parameterized Constitutive Models for Metamaterials
• Strain energy density as a Gaussian process and its utilization in stochastic finite element analysis: application to planar soft tissues
• A Generative Modeling Framework for Inferring Families of Biomechanical Constitutive Laws in Data-Sparse Regimes
• Cooperative data-driven modeling
• Single-test evaluation of directional elastic properties of anisotropic structured materials
• Data-driven methods for computational mechanics: A fair comparison between neural networks based and model-free approaches
• When invariants matter: The role of I1 and I2 in neural network models of incompressible hyperelasticity
• Biaxial characterization of soft elastomers: experiments and data-adaptive configurational forces for fracture
• Recovering Mullins damage hyperelastic behaviour with physics augmented neural networks
• Cruciform specimens biaxial extension performance relationship to constitutive identification
• Input convex neural networks: universal approximation theorem and implementation for isotropic polyconvex hyperelastic energies
• Experimental Learning of a Hyperelastic Behavior with a Physics-Augmented Neural Network
• Hybrid data-driven and physics-informed regularized learning of cyclic plasticity with Neural Networks
• Automatically Differentiable Model Updating (ADiMU): conventional, hybrid, and neural network material model discovery including history-dependency
• A computational framework for nanotrusses: input convex neural networks approach
• Precise, efficient and flexible modeling of crystallizing elastomers based on physics-augmented neural networks
• Conformal Quantile Regression for Neural Probabilistic Constitutive Modeling
• COMMET: orders-of-magnitude speed-up in finite element method via batch-vectorized neural constitutive updates
• Unsupervised Constitutive Model Discovery from Sparse and Noisy Data
• Unsupervised Material Fingerprinting: Ultra-fast hyperelastic model discovery from full-field experimental measurements
• A physics-augmented neural network framework for finite strain incompressible viscoelasticity
• 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
• Hetero-EUCLID: Interpretable model discovery for heterogeneous hyperelastic materials using stress-unsupervised learning
• Enhancing material behavior discovery using embedding-oriented Physically-Guided Neural Networks with Internal Variables