Data-driven topology optimization of spinodoid metamaterials with seamlessly tunable anisotropy

Abstract

We present a two-scale topology optimization framework for the design of macroscopic bodies with an optimized elastic response, which is achieved by means of a spatially-variant cellular architecture on the microscale. The chosen spinodoid topology for the cellular network on the microscale (which is inspired by natural microstructures forming during spinodal decomposition) admits a seamless spatial grading as well as tunable elastic anisotropy, and it is parametrized by a small set of design parameters associated with the underlying Gaussian random field. The macroscale boundary value problem is discretized by finite elements, which in addition to the displacement field continuously interpolate the microscale design parameters. By assuming a separation of scales, the local constitutive behavior on the macroscale is identified as the homogenized elastic response of the microstructure based on the local design parameters. As a departure from classical FE${}^2$-type approaches, we replace the costly microscale homogenization by a data-driven surrogate model, using deep neural networks, which accurately and efficiently maps design parameters onto the effective elasticity tensor. The model is trained on homogenized stiffness data obtained from numerical homogenization by finite elements. As an added benefit, the machine learning setup admits automatic differentiation, so that sensitivities (required for the optimization problem) can be computed exactly and without the need for numerical derivatives - a strategy that holds promise far beyond the elastic stiffness. Therefore, this framework presents a new opportunity for multiscale topology optimization based on data-driven surrogate models.

arXiv comment26 pages, 16 figures

References in corpus (2)

• Deep learning for determining a near-optimal topological design without any iteration
• The mechanical response of cellular materials with spinodal topologies

Cited by in corpus (23)

• 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
• NN-EUCLID: deep-learning hyperelasticity without stress data
• Discovering plasticity models without stress data
• Physics-Informed Neural Networks for Shell Structures
• IH-GAN: A Conditional Generative Model for Implicit Surface-Based Inverse Design of Cellular Structures
• Two-stage 2D-to-3D reconstruction of realistic microstructures: Implementation and numerical validation by effective properties
• Experiment-informed finite-strain inverse design of spinodal metamaterials
• What machine learning can do for computational solid mechanics
• Exploring the structure-property relations of thin-walled, 2D extruded lattices using neural networks
• A Morphological, Topological and Mechanical Investigation of Gyroid, Spinodoid and Dual-Lattice Algorithms as Structural Models of Trabecular Bone
• Inverse designing surface curvatures by deep learning
• HyperCAN: Hypernetwork-Driven Deep Parameterized Constitutive Models for Metamaterials
• Inverse design of spinodoid structures using Bayesian optimization
• Curvature-Guided Mechanics and Design of Spinodal and Shell-Based Architected Materials
• Algebraic Language Models for Inverse Design of Metamaterials via Diffusion Transformers
• Prospecting for Pluripotency in Metamaterial Design
• Extreme resilience and dissipation in heterogeneous disordered materials
• Bayesian-EUCLID: discovering hyperelastic material laws with uncertainties
• Hetero-EUCLID: Interpretable model discovery for heterogeneous hyperelastic materials using stress-unsupervised learning
• Constitutive Priors for Inverse Design