Deep Generative Modeling for Mechanistic-based Learning and Design of Metamaterial Systems

Abstract

Metamaterials are emerging as a new paradigmatic material system to render unprecedented and tailorable properties for a wide variety of engineering applications. However, the inverse design of metamaterial and its multiscale system is challenging due to high-dimensional topological design space, multiple local optima, and high computational cost. To address these hurdles, we propose a novel data-driven metamaterial design framework based on deep generative modeling. A variational autoencoder (VAE) and a regressor for property prediction are simultaneously trained on a large metamaterial database to map complex microstructures into a low-dimensional, continuous, and organized latent space. We show in this study that the latent space of VAE provides a distance metric to measure shape similarity, enable interpolation between microstructures and encode meaningful patterns of variation in geometries and properties. Based on these insights, systematic data-driven methods are proposed for the design of microstructure, graded family, and multiscale system. For microstructure design, the tuning of mechanical properties and complex manipulations of microstructures are easily achieved by simple vector operations in the latent space. The vector operation is further extended to generate metamaterial families with a controlled gradation of mechanical properties by searching on a constructed graph model. For multiscale metamaterial systems design, a diverse set of microstructures can be rapidly generated using VAE for target properties at different locations and then assembled by an efficient graph-based optimization method to ensure compatibility between adjacent microstructures. We demonstrate our framework by designing both functionally graded and heterogeneous metamaterial systems that achieve desired distortion behaviors.

References in corpus (5)

• Auto-Encoding Variational Bayes
• Stress Field Prediction in Cantilevered Structures Using Convolutional Neural Networks
• A topological encoding method for data-driven photonics inverse design
• METASET: Exploring Shape and Property Spaces for Data-Driven Metamaterials Design
• Two-Scale Topology Optimization with Microstructures

Cited by in corpus (29)

• Inverse-design of nonlinear mechanical metamaterials via video denoising diffusion models
• Data-Driven Design for Metamaterials and Multiscale Systems: A Review
• Unifying the design space and optimizing linear and nonlinear truss metamaterials by generative modeling
• On the use of Artificial Neural Networks in Topology Optimisation
• Tailoring Structure-borne Sound Through Bandgap Engineering in Phononic Crystals and Metamaterials: A Comprehensive Review
• Recent Advances and Applications of Machine Learning in Experimental Solid Mechanics: A Review
• Mechanical Cloak via Data-Driven Aperiodic Metamaterial Design
• IH-GAN: A Conditional Generative Model for Implicit Surface-Based Inverse Design of Cellular Structures
• Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material properties
• Machine learning-assisted design of material properties
• Mosaic Flows: A Transferable Deep Learning Framework for Solving PDEs on Unseen Domains
• Controlling auxeticity in curved-beam metamaterials via a deep generative model
• Machine Learning of Implicit Combinatorial Rules in Mechanical Metamaterials
• t-METASET: Tailoring Property Bias of Large-Scale Metamaterial Datasets through Active Learning
• What machine learning can do for computational solid mechanics
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• Remixing Functionally Graded Structures: Data-Driven Topology Optimization with Multiclass Shape Blending
• De-homogenization using Convolutional Neural Networks
• Correlated-informed neural networks: a new machine learning framework to predict pressure drop in micro-channels
• Inverse designing surface curvatures by deep learning
• Generative Inverse Design of Metamaterials with Functional Responses by Interpretable Learning
• Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization
• Data-Efficient Discovery of Hyperelastic TPMS Metamaterials with Extreme Energy Dissipation
• Prospecting for Pluripotency in Metamaterial Design
• A deep learning energy method for hyperelasticity and viscoelasticity
• Scalable Gaussian Processes for Data-Driven Design using Big Data with Categorical Factors
• Smooth Like Butter: Evaluating Multi-Lattice Transitions in Property-Augmented Latent Spaces
• Time-inversion of spatiotemporal beam dynamics using uncertainty-aware latent evolution reversal
• Evolutionary de-homogenization using a generative model for optimizing solid-porous infill structures considering the stress concentration issue