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

  title={Data-driven topology optimization of spinodoid metamaterials with seamlessly tunable anisotropy},
  author={Li Zheng and Siddhant Kumar and Dennis M. Kochmann},

FluTO: Graded Multiscale Fluid Topology Optimization using Neural Networks

Fluid-flow devices with low dissipation, but high contact area, are of importance in many applications. A well-known strategy to design such devices is multi-scale topology optimization (MTO), where

Inverse design of anisotropic spinodoid materials with prescribed diffusivity

The three-dimensional microstructure of functional materials determines its effective properties, like the mass transport properties of a porous material. Hence, it is desirable to be able to tune

Inverting the structure–property map of truss metamaterials by deep learning

A deep-learning framework, which combines neural networks with enforced physical constraints, to predict truss architectures with fully tailored anisotropic stiffness, trained on millions of unit cells is proposed.

Enhanced Cellular Materials through Multiscale, Variable-Section Inner Designs: Mechanical Attributes and Neural Network Modeling

In the current work, the mechanical response of multiscale cellular materials with hollow variable-section inner elements is analyzed, combining experimental, numerical and machine learning

The Updated Properties Model (UPM): A topology optimization algorithm for the creation of macro-micro optimized structures with variable stiffness

The design and manufacturing of high value industrial components is suffering a change of paradigm with 3D printing. In this change of paradigm, metamaterials have an important role because when a

Physics-Informed Neural Networks for Shell Structures

Novel porous structures with non-cubic symmetry: Synthesis, elastic anisotropy, and fatigue life behavior

Natural porous structures are often anisotropic in their elastic properties, i.e., they have directional variations that are related to their topology and geometry. This paper presents the synthesis

IH-GAN: A Conditional Generative Model for Implicit Surface-Based Inverse Design of Cellular Structures



Multiscale topology optimization using neural network surrogate models

Inverse-designed spinodoid metamaterials

An efficient and robust machine learning technique for the inverse design of (meta-)materials is introduced which, when applied to spinodoid topologies, enables us to generate uniform and functionally graded cellular mechanical metamaterials with tailored direction-dependent stiffness and density.

Concurrent topology optimization for cellular structures with nonuniform microstructures based on the kriging metamodel

Using the proposed method, the macrostructural topology as well as the locations and configurations of the spatially varying nonuniform microstructures can be simultaneously optimized to ensure a sufficiently large multiscale design space.

Microstructural patterns with tunable mechanical anisotropy obtained by simulating anisotropic spinodal decomposition

The generation of mechanical metamaterials with tailored effective properties through carefully engineered microstructures requires avenues to predict optimal microstructural architectures. Phase

The mechanical response of cellular materials with spinodal topologies

Topology optimization for multiscale design of porous composites with multi-domain microstructures

Simultaneous material and structural optimization by multiscale topology optimization

This paper approaches multiscale design optimization by linearizing and formulating a new way to decompose into macro and microscale design problems in such a way that solving the decomposed problems separately lead to an overall optimum solution.