A new family of Constitutive Artificial Neural Networks towards automated model discovery

Abstract

For more than 100 years, chemical, physical, and material scientists have proposed competing constitutive models to best characterize the behavior of natural and man-made materials in response to mechanical loading. Now, computer science offers a universal solution: Neural Networks. Neural Networks are powerful function approximators that can learn constitutive relations from large data without any knowledge of the underlying physics. However, classical Neural Networks ignore a century of research in constitutive modeling, violate thermodynamic considerations, and fail to predict the behavior outside the training regime. Here we design a new family of Constitutive Artificial Neural Networks that inherently satisfy common kinematic, thermodynamic, and physic constraints and, at the same time, constrain the design space of admissible functions to create robust approximators, even in the presence of sparse data. We revisit the non-linear field theories of mechanics and reverse-engineer the network input to account for material objectivity, symmetry, and incompressibility; the network output to enforce thermodynamic consistency; the activation functions to implement physically reasonable restrictions; and the network architecture to ensure polyconvexity. We demonstrate that this new class of models is a generalization of the classical neo Hooke, Blatz Ko, Mooney Rivlin, Yeoh, and Demiray models and that the network weights have a clear physical interpretation. When trained with classical benchmark data for rubber, our network autonomously selects the best constitutive model and learns its parameters. Our findings suggests that Constitutive Artificial Neural Networks have the potential to induce a paradigm shift in constitutive modeling, from user-defined model selection to automated model discovery. Our source code, data, and examples are available at https://github.com/LivingMatterLab/CANN.

31 pages, 14 figures

References in corpus (10)

• Integrating Machine Learning and Multiscale Modeling: Perspectives, Challenges, and Opportunities in the Biological, Biomedical, and Behavioral Sciences
• Thermodynamics-based Artificial Neural Networks for constitutive modeling
• Polyconvex anisotropic hyperelasticity with neural networks
• PySINDy: A comprehensive Python package for robust sparse system identification
• Bayesian Physics-Informed Neural Networks for real-world nonlinear dynamical systems
• Multiscale modeling of inelastic materials with Thermodynamics-based Artificial Neural Networks (TANN)
• NN-EUCLID: deep-learning hyperelasticity without stress data
• Data-driven Tissue Mechanics with Polyconvex Neural Ordinary Differential Equations
• Model-free Data-Driven Computational Mechanics Enhanced by Tensor Voting
• A Physics-informed Assembly of Feed-Forward Neural Network Engines to Predict Inelasticity in Cross-Linked Polymers

Cited by in corpus (37)

• Neural networks meet hyperelasticity: A guide to enforcing physics
• Deep Learning in Deterministic Computational Mechanics
• Theory and implementation of inelastic Constitutive Artificial Neural Networks
• Automated discovery of interpretable hyperelastic material models for human brain tissue with EUCLID
• Data-driven anisotropic finite viscoelasticity using neural ordinary differential equations
• Combining physics-based and data-driven models: advancing the frontiers of research with Scientific Machine Learning
• Discovering interpretable elastoplasticity models via the neural polynomial method enabled symbolic regressions
• 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
• Automated Data-Driven Discovery of Material Models Based on Symbolic Regression: A Case Study on Human Brain Cortex
• Multiscale topology optimization of functionally graded lattice structures based on physics-augmented neural network material models
• A universal material model subroutine for soft matter systems
• A Generative Modeling Framework for Inferring Families of Biomechanical Constitutive Laws in Data-Sparse Regimes
• Automated Model Discovery for Tensional Homeostasis: Constitutive Machine Learning in Growth and Remodeling
• 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
• Similarity Equivariant Graph Neural Networks for Homogenization of Metamaterials
• Biaxial characterization of soft elastomers: experiments and data-adaptive configurational forces for fracture
• Recovering Mullins damage hyperelastic behaviour with physics augmented neural networks
• A generalized dual potential for inelastic Constitutive Artificial Neural Networks: A JAX implementation at finite strains
• Cruciform specimens biaxial extension performance relationship to constitutive identification
• Input convex neural networks: universal approximation theorem and implementation for isotropic polyconvex hyperelastic energies
• A Complement to Neural Networks for Anisotropic Inelasticity at Finite Strains
• In search of constitutive conditions in isotropic hyperelasticity: polyconvexity versus true-stress-true-strain monotonicity
• Hybrid data-driven and physics-informed regularized learning of cyclic plasticity with Neural Networks
• Experimental Learning of a Hyperelastic Behavior with a Physics-Augmented Neural Network
• A computational framework for nanotrusses: input convex neural networks approach
• Conformal Quantile Regression for Neural Probabilistic Constitutive Modeling
• COMMET: orders-of-magnitude speed-up in finite element method via batch-vectorized neural constitutive updates
• FEBio FINESSE: An open-source finite element simulation approach to estimate in vivo heart valve strains using shape enforcement
• Hammering at the entropy: A GENERIC-guided approach to learning polymeric rheological constitutive equations using PINNs
• Unsupervised Material Fingerprinting: Ultra-fast hyperelastic model discovery from full-field experimental measurements
• Learning inelastic constitutive models from stress-strain data under hard thermodynamic constraints
• A Convex Route to Thermoelasticity: Learning Internal Energy and Dissipation
• Learning ultra-compressible hyperelasticity with splines: Constitutive asymmetries and non-unique representations
• Hetero-EUCLID: Interpretable model discovery for heterogeneous hyperelastic materials using stress-unsupervised learning