TOMAS: Topology Optimization of Multiscale Fluid Devices using Variational Autoencoders and Super-Shapes

TL;DR

This paper introduces a novel multiscale topology optimization framework for fluid devices that leverages variational autoencoders and super-shape microstructures to efficiently design microstructures and optimize fluid flow.

Contribution

It combines a VAE-based latent space with super-shape microstructures for efficient multiscale fluid device optimization, enabling the use of new microstructures beyond the original dataset.

Findings

Successfully optimized fluid devices in 2D examples.

Demonstrated the ability to generate new microstructures.

Reduced computational cost by avoiding repeated homogenization.

Abstract

In this paper, we present a framework for multiscale topology optimization of fluid-flow devices. The objective is to minimize dissipated power, subject to a desired contact-area. The proposed strategy is to design optimal microstructures in individual finite element cells, while simultaneously optimizing the overall fluid flow. In particular, parameterized super-shape microstructures are chosen here to represent microstructures since they exhibit a wide range of permeability and contact area. To avoid repeated homogenization, a finite set of these super-shapes are analyzed a priori, and a variational autoencoder (VAE) is trained on their fluid constitutive properties (permeability), contact area and shape parameters. The resulting differentiable latent space is integrated with a coordinate neural network to carry out a global multi-scale fluid flow optimization. The latent space enables the use of new microstructures that were not present in the original data-set. The proposed method is illustrated using numerous examples in 2D.