2-dimensional stress field prediction using deep learning

Computational solid mechanics has been widely conducted using Finite Element Analysis (FEA). However, to do structural analysis on an object, many processes have to be done after setting up the geometry and boundary conditions for final analysis of the structure using Finite Element Method (FEM)....

Full description

Saved in:
Bibliographic Details
Main Author: Yeo, Roselyn Yan Ling
Other Authors: Lee Yong Tsui
Format: Final Year Project
Language:English
Published: 2019
Subjects:
Online Access:http://hdl.handle.net/10356/76460
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-76460
record_format dspace
spelling sg-ntu-dr.10356-764602023-03-04T19:11:29Z 2-dimensional stress field prediction using deep learning Yeo, Roselyn Yan Ling Lee Yong Tsui School of Mechanical and Aerospace Engineering DRNTU::Engineering::Manufacturing Computational solid mechanics has been widely conducted using Finite Element Analysis (FEA). However, to do structural analysis on an object, many processes have to be done after setting up the geometry and boundary conditions for final analysis of the structure using Finite Element Method (FEM). With the progress of deep learning, conditional Generative Adversarial Network (cGAN) has shown great potential in solving FEA problems quickly and accurately. In this project, a cGAN architecture was developed and 2D structures with arbitrary geometries and boundary conditions were trained on the network. The network was trained to directly output Von Mises stress distribution plots over the structure. The trained network produced predicted outputs with a mean relative error of 4% with respect to the average ground truth. cGANs have great potential of being generalised and applied to more complex structures with more complex boundary conditions. Bachelor of Engineering (Mechanical Engineering) 2019-03-21T02:29:50Z 2019-03-21T02:29:50Z 2019 Final Year Project (FYP) http://hdl.handle.net/10356/76460 en Nanyang Technological University 100 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Manufacturing
spellingShingle DRNTU::Engineering::Manufacturing
Yeo, Roselyn Yan Ling
2-dimensional stress field prediction using deep learning
description Computational solid mechanics has been widely conducted using Finite Element Analysis (FEA). However, to do structural analysis on an object, many processes have to be done after setting up the geometry and boundary conditions for final analysis of the structure using Finite Element Method (FEM). With the progress of deep learning, conditional Generative Adversarial Network (cGAN) has shown great potential in solving FEA problems quickly and accurately. In this project, a cGAN architecture was developed and 2D structures with arbitrary geometries and boundary conditions were trained on the network. The network was trained to directly output Von Mises stress distribution plots over the structure. The trained network produced predicted outputs with a mean relative error of 4% with respect to the average ground truth. cGANs have great potential of being generalised and applied to more complex structures with more complex boundary conditions.
author2 Lee Yong Tsui
author_facet Lee Yong Tsui
Yeo, Roselyn Yan Ling
format Final Year Project
author Yeo, Roselyn Yan Ling
author_sort Yeo, Roselyn Yan Ling
title 2-dimensional stress field prediction using deep learning
title_short 2-dimensional stress field prediction using deep learning
title_full 2-dimensional stress field prediction using deep learning
title_fullStr 2-dimensional stress field prediction using deep learning
title_full_unstemmed 2-dimensional stress field prediction using deep learning
title_sort 2-dimensional stress field prediction using deep learning
publishDate 2019
url http://hdl.handle.net/10356/76460
_version_ 1759855778525609984