mcGANs: Topology Optimization Using Multi-Stage CGAN

The traditional methods of solving topology optimization depends on finite element method (FEM). However, the iterative calculation of FEM increases the time cost of topology optimization significantly. In this paper, a novel strategy based on deep learning is proposed to speed up the topology optim...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiandong Zhu, Ting Ding, Fuhao Cui, Zhi Wang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11002494/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849736934599950336
author Jiandong Zhu
Ting Ding
Fuhao Cui
Zhi Wang
author_facet Jiandong Zhu
Ting Ding
Fuhao Cui
Zhi Wang
author_sort Jiandong Zhu
collection DOAJ
description The traditional methods of solving topology optimization depends on finite element method (FEM). However, the iterative calculation of FEM increases the time cost of topology optimization significantly. In this paper, a novel strategy based on deep learning is proposed to speed up the topology optimization process. Conditional Generative Adversarial Network (CGAN) is used as the basic network in which the constraints of optimization are taken into consideration as the conditions of generation. Additionally, the stress and strain are generated from initial physical information by networks, and used as the inputs of optimization network. The cascaded network can realize structural topology optimization without iterative calculations in the whole process. In the experiments, the traditional Solid Isotropic Material with Penalization (SIMP) method was replicated and implemented multiple times. It was found that the SIMP method takes 30 - 40 seconds to conduct topology optimization, while the proposed mcGANs only need 1.7682 seconds. Moreover, performance indicators such as Mean Absolute Error (MAE), Mean Squared Error (MSE), and Peak Signal-to-Noise Ratio (PSNR) are used to evaluate the performance of mcGANs, which demonstrate the effectiveness and superiority of this strategy.
format Article
id doaj-art-e9b6e2a3202d4af9a764d383222963d3
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-e9b6e2a3202d4af9a764d383222963d32025-08-20T03:07:06ZengIEEEIEEE Access2169-35362025-01-0113839058391510.1109/ACCESS.2025.356940411002494mcGANs: Topology Optimization Using Multi-Stage CGANJiandong Zhu0https://orcid.org/0009-0009-1722-0695Ting Ding1Fuhao Cui2https://orcid.org/0009-0002-4891-965XZhi Wang3https://orcid.org/0000-0002-9652-7274Henan High-Speed Railway Operation and Maintenance Engineering Research Center, Zhengzhou, ChinaHenan High-Speed Railway Operation and Maintenance Engineering Research Center, Zhengzhou, ChinaHenan High-Speed Railway Operation and Maintenance Engineering Research Center, Zhengzhou, ChinaYantai City College of Science and Technology, Yantai, ChinaThe traditional methods of solving topology optimization depends on finite element method (FEM). However, the iterative calculation of FEM increases the time cost of topology optimization significantly. In this paper, a novel strategy based on deep learning is proposed to speed up the topology optimization process. Conditional Generative Adversarial Network (CGAN) is used as the basic network in which the constraints of optimization are taken into consideration as the conditions of generation. Additionally, the stress and strain are generated from initial physical information by networks, and used as the inputs of optimization network. The cascaded network can realize structural topology optimization without iterative calculations in the whole process. In the experiments, the traditional Solid Isotropic Material with Penalization (SIMP) method was replicated and implemented multiple times. It was found that the SIMP method takes 30 - 40 seconds to conduct topology optimization, while the proposed mcGANs only need 1.7682 seconds. Moreover, performance indicators such as Mean Absolute Error (MAE), Mean Squared Error (MSE), and Peak Signal-to-Noise Ratio (PSNR) are used to evaluate the performance of mcGANs, which demonstrate the effectiveness and superiority of this strategy.https://ieeexplore.ieee.org/document/11002494/Deep learningtopology optimizationcGANU-NetSE-ResNet
spellingShingle Jiandong Zhu
Ting Ding
Fuhao Cui
Zhi Wang
mcGANs: Topology Optimization Using Multi-Stage CGAN
IEEE Access
Deep learning
topology optimization
cGAN
U-Net
SE-ResNet
title mcGANs: Topology Optimization Using Multi-Stage CGAN
title_full mcGANs: Topology Optimization Using Multi-Stage CGAN
title_fullStr mcGANs: Topology Optimization Using Multi-Stage CGAN
title_full_unstemmed mcGANs: Topology Optimization Using Multi-Stage CGAN
title_short mcGANs: Topology Optimization Using Multi-Stage CGAN
title_sort mcgans topology optimization using multi stage cgan
topic Deep learning
topology optimization
cGAN
U-Net
SE-ResNet
url https://ieeexplore.ieee.org/document/11002494/
work_keys_str_mv AT jiandongzhu mcganstopologyoptimizationusingmultistagecgan
AT tingding mcganstopologyoptimizationusingmultistagecgan
AT fuhaocui mcganstopologyoptimizationusingmultistagecgan
AT zhiwang mcganstopologyoptimizationusingmultistagecgan