國立虎尾科技大學 |

Deep Learning Frameworks for Structural Topology Optimization.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Deep Learning Frameworks for Structural Topology Optimization./
作者:	Rade, Jaydeep Ravindra.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	62 p.
附註:	Source: Masters Abstracts International, Volume: 83-01.
Contained By:	Masters Abstracts International83-01.
標題:	Mechanical engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28259344
ISBN:	9798516903915

Deep Learning Frameworks for Structural Topology Optimization.
Rade, Jaydeep Ravindra.

Deep Learning Frameworks for Structural Topology Optimization. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 62 p.

Source: Masters Abstracts International, Volume: 83-01.

Thesis (M.S.)--Iowa State University, 2021.

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

Topology optimization has emerged as a popular approach to refine a component's design and increasing its performance. However, current state-of-the-art topology optimization frameworks are compute-intensive, mainly due to multiple finite element analysis iterations required to evaluate the component's performance during the optimization process. Recently, machine learning-based topology optimization methods have been explored by researchers to alleviate this issue. However, previous approaches have mainly been demonstrated on simple two-dimensional applications with low-resolution geometry. Further, current methods are based on a single machine learning model for end-to-end prediction, which requires a large dataset for training. These challenges make it non-trivial to extend the current approaches to higher resolutions.In this thesis, we explore deep learning-based frameworks that are consistent with traditional topology optimization algorithms for three-dimensional topology optimization with a reasonably fine (high) resolution. We achieve this by training multiple networks, each trying to learn a different step of the overall topology optimization methodology, making the framework more consistent with the topology optimization algorithm. We demonstrate the application of our framework on both 2D and 3D geometries. The results show that our approach predicts the final optimized design better than current ML-based topology optimization methods.

ISBN: 9798516903915Subjects--Topical Terms:

557493
Mechanical engineering.
Subjects--Index Terms:

Algorithmically-consistent learning

Deep Learning Frameworks for Structural Topology Optimization.
LDR:02682nam a2200397 4500 001 1067154
005 20220823142303.5
008 221020s2021 ||||||||||||||||| ||eng d
020 $a 9798516903915
035 $a (MiAaPQ)AAI28259344
035 $a AAI28259344
040 $a MiAaPQ $c MiAaPQ
100 1 $a Rade, Jaydeep Ravindra. $0 (orcid)0000-0002-6831-8416 $3 1372503
245 1 0 $a Deep Learning Frameworks for Structural Topology Optimization.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 62 p.
500 $a Source: Masters Abstracts International, Volume: 83-01.
500 $a Advisor: Krishnamurthy, Adarsh;Sarkar, Soumik.
502 $a Thesis (M.S.)--Iowa State University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Topology optimization has emerged as a popular approach to refine a component's design and increasing its performance. However, current state-of-the-art topology optimization frameworks are compute-intensive, mainly due to multiple finite element analysis iterations required to evaluate the component's performance during the optimization process. Recently, machine learning-based topology optimization methods have been explored by researchers to alleviate this issue. However, previous approaches have mainly been demonstrated on simple two-dimensional applications with low-resolution geometry. Further, current methods are based on a single machine learning model for end-to-end prediction, which requires a large dataset for training. These challenges make it non-trivial to extend the current approaches to higher resolutions.In this thesis, we explore deep learning-based frameworks that are consistent with traditional topology optimization algorithms for three-dimensional topology optimization with a reasonably fine (high) resolution. We achieve this by training multiple networks, each trying to learn a different step of the overall topology optimization methodology, making the framework more consistent with the topology optimization algorithm. We demonstrate the application of our framework on both 2D and 3D geometries. The results show that our approach predicts the final optimized design better than current ML-based topology optimization methods.
590 $a School code: 0097.
650 4 $a Mechanical engineering. $3 557493
650 4 $a Artificial intelligence. $3 559380
650 4 $a Engineering. $3 561152
650 4 $a Design. $3 595500
650 4 $a Electrical engineering. $3 596380
653 $a Algorithmically-consistent learning
653 $a Deep learning
653 $a Sequence models
653 $a Topology optimization
653 $a Three-dimensional topology
690 $a 0544
690 $a 0389
690 $a 0800
690 $a 0548
690 $a 0537
710 2 $a Iowa State University. $b Electrical and Computer Engineering. $3 1179387
773 0 $t Masters Abstracts International $g 83-01.
790 $a 0097
791 $a M.S.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28259344