HyperCAN: Hypernetwork-Driven Deep Parameterized Constitutive Models for Metamaterials

Abstract

We introduce HyperCAN, a machine learning framework that utilizes hypernetworks to construct adaptable constitutive artificial neural networks for a wide range of beam-based metamaterials exhibiting diverse mechanical behavior under finite deformations. HyperCAN integrates an input convex network that models the nonlinear stress-strain map of a truss lattice, while ensuring adherence to fundamental mechanics principles, along with a hypernetwork that dynamically adjusts the parameters of the convex network as a function of the lattice topology and geometry. This unified framework demonstrates robust generalization in predicting the mechanical behavior of previously unseen metamaterial designs and loading scenarios well beyond the training domain. We show how HyperCAN can be integrated into multiscale simulations to accurately capture the highly nonlinear responses of large-scale truss metamaterials, closely matching fully resolved simulations while significantly reducing computational costs. This offers new efficient opportunities for the multiscale design and optimization of truss metamaterials.

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• Data-driven computational mechanics
• Bistable Auxetic Mechanical Metamaterials Inspired by Ancient Geometric Motifs
• Geometric deep learning for computational mechanics Part I: Anisotropic Hyperelasticity
• Unifying the design space and optimizing linear and nonlinear truss metamaterials by generative modeling
• Data-driven topology optimization of spinodoid metamaterials with seamlessly tunable anisotropy
• Learning Constitutive Relations from Indirect Observations Using Deep Neural Networks
• NN-EUCLID: deep-learning hyperelasticity without stress data
• Discovering plasticity models without stress data
• Local approximate Gaussian process regression for data-driven constitutive laws: Development and comparison with neural networks
• Physics-informed Data-driven Discovery of Constitutive Models with Application to Strain-Rate-sensitive Soft Materials
• Learning the Pareto Front with Hypernetworks
• Topology Optimization of Graded Truss Lattices Based on On-the-Fly Homogenization
• Inverse designing surface curvatures by deep learning
• HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networks
• Machine learning materials physics: Deep neural networks trained on elastic free energy data from martensitic microstructures predict homogenized stress fields with high accuracy
• HyperPINN: Learning parameterized differential equations with physics-informed hypernetworks
• Predicting deformation mechanisms in architected metamaterials using GNN
• HyperTTS: Parameter Efficient Adaptation in Text to Speech using Hypernetworks

Cited by in corpus (2)

• Can KAN CANs? Input-convex Kolmogorov-Arnold Networks (KANs) as hyperelastic constitutive artificial neural networks (CANs)
• COMMET: orders-of-magnitude speed-up in finite element method via batch-vectorized neural constitutive updates