TopologyGAN: Topology Optimization Using Generative Adversarial Networks Based on Physical Fields Over the Initial Domain

03/05/2020
by   Zhenguo Nie, et al.
0

In topology optimization using deep learning, load and boundary conditions represented as vectors or sparse matrices often miss the opportunity to encode a rich view of the design problem, leading to less than ideal generalization results. We propose a new data-driven topology optimization model called TopologyGAN that takes advantage of various physical fields computed on the original, unoptimized material domain, as inputs to the generator of a conditional generative adversarial network (cGAN). Compared to a baseline cGAN, TopologyGAN achieves a nearly 3× reduction in the mean squared error and a 2.5× reduction in the mean absolute error on test problems involving previously unseen boundary conditions. Built on several existing network models, we also introduce a hybrid network called U-SE(Squeeze-and-Excitation)-ResNet for the generator that further increases the overall accuracy. We publicly share our full implementation and trained network.

READ FULL TEXT

page 2

page 6

page 7

page 8

page 10

page 12

page 13

page 15

research
05/07/2021

GANTL: Towards Practical and Real-Time Topology Optimization with Conditional GANs and Transfer Learning

Many machine learning methods have been recently developed to circumvent...
research
08/03/2023

Deep Learning-based Prediction of Stress and Strain Maps in Arterial Walls for Improved Cardiovascular Risk Assessment

This study investigated the potential of end-to-end deep learning tools ...
research
09/22/2022

Fluidic Topology Optimization with an Anisotropic Mixture Model

Fluidic devices are crucial components in many industrial applications i...
research
04/11/2020

Deep learning-based topological optimization for representing a user-specified design area

Presently, topology optimization requires multiple iterations to create ...
research
02/09/2021

Regularized Generative Adversarial Network

We propose a framework for generating samples from a probability distrib...
research
08/03/2018

A novel topology design approach using an integrated deep learning network architecture

Topology design optimization offers tremendous opportunity in design and...
research
11/29/2021

Continuous conditional generative adversarial networks for data-driven solutions of poroelasticity with heterogeneous material properties

Machine learning-based data-driven modeling can allow computationally ef...

Please sign up or login with your details

Forgot password? Click here to reset