3D Shape Synthesis for Conceptual Design and Optimization Using Variational Autoencoders

04/16/2019
by   Wentai Zhang, et al.
0

We propose a data-driven 3D shape design method that can learn a generative model from a corpus of existing designs, and use this model to produce a wide range of new designs. The approach learns an encoding of the samples in the training corpus using an unsupervised variational autoencoder-decoder architecture, without the need for an explicit parametric representation of the original designs. To facilitate the generation of smooth final surfaces, we develop a 3D shape representation based on a distance transformation of the original 3D data, rather than using the commonly utilized binary voxel representation. Once established, the generator maps the latent space representations to the high-dimensional distance transformation fields, which are then automatically surfaced to produce 3D representations amenable to physics simulations or other objective function evaluation modules. We demonstrate our approach for the computational design of gliders that are optimized to attain prescribed performance scores. Our results show that when combined with genetic optimization, the proposed approach can generate a rich set of candidate concept designs that achieve prescribed functional goals, even when the original dataset has only a few or no solutions that achieve these goals.

READ FULL TEXT

page 4

page 8

page 9

page 10

research
06/21/2020

Airfoil Design Parameterization and Optimization using Bézier Generative Adversarial Networks

Global optimization of aerodynamic shapes usually requires a large numbe...
research
03/09/2020

Automating Representation Discovery with MAP-Elites

The way solutions are represented, or encoded, is usually the result of ...
research
04/29/2023

ShipHullGAN: A generic parametric modeller for ship hull design using deep convolutional generative model

In this work, we introduce ShipHullGAN, a generic parametric modeller bu...
research
08/05/2018

3D Conceptual Design Using Deep Learning

This article proposes a data-driven methodology to achieve a fast design...
research
06/26/2023

Unifying the design space of truss metamaterials by generative modeling

The rise of machine learning has fueled the discovery of new materials a...
research
01/12/2021

Airfoil GAN: Encoding and Synthesizing Airfoils forAerodynamic-aware Shape Optimization

The current design of aerodynamic shapes, like airfoils, involves comput...
research
06/10/2020

Computational Design and Evaluation Methods for Empowering Non-Experts in Digital Fabrication

Despite the increasing availability of personal fabrication hardware and...

Please sign up or login with your details

Forgot password? Click here to reset