Unifying the design space and optimizing linear and nonlinear truss metamaterials by generative modeling

Abstract

The rise of machine learning has fueled the discovery of new materials and, especially, metamaterials--truss lattices being their most prominent class. While their tailorable properties have been explored extensively, the design of truss-based metamaterials has remained highly limited and often heuristic, due to the vast, discrete design space and the lack of a comprehensive parameterization. We here present a graph-based deep learning generative framework, which combines a variational autoencoder and a property predictor, to construct a reduced, continuous latent representation covering an enormous range of trusses. This unified latent space allows for the fast generation of new designs through simple operations (e.g., traversing the latent space or interpolating between structures). We further demonstrate an optimization framework for the inverse design of trusses with customized mechanical properties in both the linear and nonlinear regimes, including designs exhibiting exceptionally stiff, auxetic, pentamode-like, and tailored nonlinear behaviors. This generative model can predict manufacturable (and counter-intuitive) designs with extreme target properties beyond the training domain.

References in corpus (17)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Automatic chemical design using a data-driven continuous representation of molecules
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• A Generative Model for Inverse Design of Metamaterials
• Convolutional Networks on Graphs for Learning Molecular Fingerprints
• DeepInf: Social Influence Prediction with Deep Learning
• Mechanical Metamaterials with Negative Compressibility Transitions
• Deep Generative Modeling for Mechanistic-based Learning and Design of Metamaterial Systems
• 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
• Graph Neural Networks for an Accurate and Interpretable Prediction of the Properties of Polycrystalline Materials
• Model-data-driven constitutive responses: application to a multiscale computational framework
• ControlVAE: Controllable Variational Autoencoder
• Geometric deep learning for computational mechanics Part II: Graph embedding for interpretable multiscale plasticity
• Joint embedding of structure and features via graph convolutional networks
• Equivariant geometric learning for digital rock physics: estimating formation factor and effective permeability tensors from Morse graph

Cited by in corpus (12)

• Unifying the design space and optimizing linear and nonlinear truss metamaterials by generative modeling
• AI-guided inverse design and discovery of recyclable vitrimeric polymers
• HyperCAN: Hypernetwork-Driven Deep Parameterized Constitutive Models for Metamaterials
• LatticeGraphNet: A two-scale graph neural operator for simulating lattice structures
• On the data-driven description of lattice materials mechanics
• Piezoelectric truss metamaterials: data-driven design and additive manufacturing
• Investigation on optimal microstructure of dual-phase steel with high strength and ductility by machine learning
• Algebraic Language Models for Inverse Design of Metamaterials via Diffusion Transformers
• Universal Fourier Neural Operators for periodic homogenization problems in linear elasticity
• Irregular Metamaterial Networks
• Continuous Design and Reprogramming of Totimorphic Structures for Space Applications
• Geometric quantification for nonlinear deformation in knitted fabrics