Topology optimization using artificial intelligence

An analysis of topology optimization employing deep learning, namely Generative Adversarial Networks (GANs), and topology optimization utilizing the Solid Isotropic Material with Penalization (SIMP) method is presented in this research. We describe the theoretical foundations of GANs and th...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmed Ait Ouchaoui, Mohammed Nassraoui, Bouchaib Radi
Format: Article
Language:English
Published: ISTE Group 2024-01-01
Series:Incertitudes et Fiabilité des Systèmes Multiphysiques
Online Access:https://www.openscience.fr/Topology-optimization-using-artificial-intelligence
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849326631066271744
author Ahmed Ait Ouchaoui
Mohammed Nassraoui
Bouchaib Radi
author_facet Ahmed Ait Ouchaoui
Mohammed Nassraoui
Bouchaib Radi
author_sort Ahmed Ait Ouchaoui
collection DOAJ
description An analysis of topology optimization employing deep learning, namely Generative Adversarial Networks (GANs), and topology optimization utilizing the Solid Isotropic Material with Penalization (SIMP) method is presented in this research. We describe the theoretical foundations of GANs and the SIMP technique. A cantilever beam with predetermined boundary conditions was the topic of a static study to show the practical efficacy of these methods. The structural performance parameters, such as maximal directional displacement, maximal Von Mises stress, and deformation energy. The findings show that deep learning-based topology optimization, as demonstrated by TopologyGAN, provides considerable benefits in terms of improved design correctness and computing performance.
format Article
id doaj-art-c38fff676a2b4d7abdd06b57c7e78b15
institution Kabale University
issn 2514-569X
language English
publishDate 2024-01-01
publisher ISTE Group
record_format Article
series Incertitudes et Fiabilité des Systèmes Multiphysiques
spelling doaj-art-c38fff676a2b4d7abdd06b57c7e78b152025-08-20T03:48:06ZengISTE GroupIncertitudes et Fiabilité des Systèmes Multiphysiques2514-569X2024-01-0182384210.21494/ISTE.OP.2024.1231Topology optimization using artificial intelligenceAhmed Ait OuchaouiMohammed NassraouiBouchaib Radi An analysis of topology optimization employing deep learning, namely Generative Adversarial Networks (GANs), and topology optimization utilizing the Solid Isotropic Material with Penalization (SIMP) method is presented in this research. We describe the theoretical foundations of GANs and the SIMP technique. A cantilever beam with predetermined boundary conditions was the topic of a static study to show the practical efficacy of these methods. The structural performance parameters, such as maximal directional displacement, maximal Von Mises stress, and deformation energy. The findings show that deep learning-based topology optimization, as demonstrated by TopologyGAN, provides considerable benefits in terms of improved design correctness and computing performance.https://www.openscience.fr/Topology-optimization-using-artificial-intelligence
spellingShingle Ahmed Ait Ouchaoui
Mohammed Nassraoui
Bouchaib Radi
Topology optimization using artificial intelligence
Incertitudes et Fiabilité des Systèmes Multiphysiques
title Topology optimization using artificial intelligence
title_full Topology optimization using artificial intelligence
title_fullStr Topology optimization using artificial intelligence
title_full_unstemmed Topology optimization using artificial intelligence
title_short Topology optimization using artificial intelligence
title_sort topology optimization using artificial intelligence
url https://www.openscience.fr/Topology-optimization-using-artificial-intelligence
work_keys_str_mv AT ahmedaitouchaoui topologyoptimizationusingartificialintelligence
AT mohammednassraoui topologyoptimizationusingartificialintelligence
AT bouchaibradi topologyoptimizationusingartificialintelligence