國立高雄大學圖資館 |

Language: English

Back

Standard and Inception-based Encoder...

O'Neill, Nathanial James.

Standard and Inception-based Encoder-Decoder Neural Networks for Predicting the Solution Convergence of Design Optimization Algorithms.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Standard and Inception-based Encoder-Decoder Neural Networks for Predicting the Solution Convergence of Design Optimization Algorithms.
Author:	O'Neill, Nathanial James.
Published:	Ann Arbor : ProQuest Dissertations & Theses, 2019
Description:	82 p.
Notes:	Source: Masters Abstracts International, Volume: 81-03.
Notes:	Advisor: Maute, Kurt.
Contained By:	Masters Abstracts International81-03.
Subject:	Aerospace engineering.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13864226
ISBN:	9781085623483

Standard and Inception-based Encoder-Decoder Neural Networks for Predicting the Solution Convergence of Design Optimization Algorithms.
O'Neill, Nathanial James.

Standard and Inception-based Encoder-Decoder Neural Networks for Predicting the Solution Convergence of Design Optimization Algorithms. - Ann Arbor : ProQuest Dissertations & Theses, 2019 - 82 p.

Source: Masters Abstracts International, Volume: 81-03.

Thesis (M.S.)--University of Colorado at Boulder, 2019.

This item must not be sold to any third party vendors.

The goal of this work is to investigate the ways in which the capabilities of machine learning algorithms, specifically those of neural networks, can be leveraged to enhance the performance of design optimization algorithms -- specifically those of topology optimization.A recent boom of interest in design optimization has occurred, coinciding with the arrival and development of advanced manufacturing techniques (such as 3D printing and additive manufacturing) which are compatible with the designs generated by these algorithms. Neural networks have seen an even larger boom in interest and development for their ability to act as ``universal function generators;" in other words, for their ability to learn highly non-linear functions that approximate the behavior of extremely complex systems. Merging design optimization algorithms with the capabilities of neural networks poses several distinct possibilities: drastically reducing optimization time by predicting solution convergence; up-scaling solution resolution using Generative Adversarial Networks (GAN's); predicting solutions with no iteration; predicting and recognizing features in the optimized solution, just to name a few.In this thesis, three neural network architectures are tested for their ability to act as solution convergence predictors of a density-based topology optimization solver. The problem is posed as an image segmentation problem, and the neural networks are all trained on a 40,000 example training set with each example containing 100 iterations from the open source optimization solver Topy, (a data set created by Sosnovik et al (2017)). The third network developed and tested is a novel hybrid network -- an inception encoder-decoder network -- which is found to outperform the other networks on the prediction task at hand.

ISBN: 9781085623483Subjects--Topical Terms:

324294
Aerospace engineering.

Standard and Inception-based Encoder-Decoder Neural Networks for Predicting the Solution Convergence of Design Optimization Algorithms.
LDR:02853nmm a2200313 4500 001 570758
005 20200514111952.5
008 200901s2019 ||||||||||||||||| ||eng d
020 $a 9781085623483
035 $a (MiAaPQ)AAI13864226
035 $a AAI13864226
040 $a MiAaPQ $c MiAaPQ
100 1 $a O'Neill, Nathanial James. $3 857445
245 1 0 $a Standard and Inception-based Encoder-Decoder Neural Networks for Predicting the Solution Convergence of Design Optimization Algorithms.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2019
300 $a 82 p.
500 $a Source: Masters Abstracts International, Volume: 81-03.
500 $a Advisor: Maute, Kurt.
502 $a Thesis (M.S.)--University of Colorado at Boulder, 2019.
506 $a This item must not be sold to any third party vendors.
520 $a The goal of this work is to investigate the ways in which the capabilities of machine learning algorithms, specifically those of neural networks, can be leveraged to enhance the performance of design optimization algorithms -- specifically those of topology optimization.A recent boom of interest in design optimization has occurred, coinciding with the arrival and development of advanced manufacturing techniques (such as 3D printing and additive manufacturing) which are compatible with the designs generated by these algorithms. Neural networks have seen an even larger boom in interest and development for their ability to act as ``universal function generators;" in other words, for their ability to learn highly non-linear functions that approximate the behavior of extremely complex systems. Merging design optimization algorithms with the capabilities of neural networks poses several distinct possibilities: drastically reducing optimization time by predicting solution convergence; up-scaling solution resolution using Generative Adversarial Networks (GAN's); predicting solutions with no iteration; predicting and recognizing features in the optimized solution, just to name a few.In this thesis, three neural network architectures are tested for their ability to act as solution convergence predictors of a density-based topology optimization solver. The problem is posed as an image segmentation problem, and the neural networks are all trained on a 40,000 example training set with each example containing 100 iterations from the open source optimization solver Topy, (a data set created by Sosnovik et al (2017)). The third network developed and tested is a novel hybrid network -- an inception encoder-decoder network -- which is found to outperform the other networks on the prediction task at hand.
590 $a School code: 0051.
650 4 $a Aerospace engineering. $3 324294
650 4 $a Computer science. $3 199325
650 4 $a Mechanical engineering. $3 190348
690 $a 0538
690 $a 0984
690 $a 0548
710 2 $a University of Colorado at Boulder. $b Aerospace Engineering. $3 857329
773 0 $t Masters Abstracts International $g 81-03.
790 $a 0051
791 $a M.S.
792 $a 2019
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13864226