東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Inverse Design and Optimization for ...

Yannuwar, Sanket Vikrant,

Linked to FindBook

Google Book

Amazon

博客來

Inverse Design and Optimization for Impingement Jet Cooling Using Variational Autoencoder /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Inverse Design and Optimization for Impingement Jet Cooling Using Variational Autoencoder // Sanket Vikrant Yannuwar.
Author:	Yannuwar, Sanket Vikrant,
Description:	1 electronic resource (72 pages)
Notes:	Source: Masters Abstracts International, Volume: 85-06.
Contained By:	Masters Abstracts International85-06.
Subject:	Design. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30727223
ISBN:	9798381021639

Inverse Design and Optimization for Impingement Jet Cooling Using Variational Autoencoder /
Yannuwar, Sanket Vikrant,

Inverse Design and Optimization for Impingement Jet Cooling Using Variational Autoencoder /Sanket Vikrant Yannuwar. - 1 electronic resource (72 pages)

Source: Masters Abstracts International, Volume: 85-06.

The focus of this study is to investigate the effectiveness of Variational Autoencoder (VAE) in solving the inverse design heat transfer problem of impingement cooling of a flat plate heat exchanger. Initially, data generation using Ansys Fluent was found to be computationally expensive and time-consuming. Therefore, I explored correlations developed from different research works on impingement cooling to save time and benchmark the application of VAE. The Florschuetz [1] correlation, which determines the impact of Reynolds number, array configuration, pitch to diameter ratio, and height to diameter ratio on crossflow and Nusselt number, was selected as these parameters have significant effects on the heat transfer and pressure drop. A dataset of 20,000 design points was generated, each having either 25 or 223 features that describe the design. Different VAE architectures were trained for inverse design, and the effects of various hyperparameters were explored. The testing loss was found to be within 5%. Additionally, the pressure drop due to crossflow was calculated, and a genetic algorithm was employed to determine the optimal design that generates the required Nusselt number while minimizing pressure drop. Overall, this study demonstrates the potential of VAEs in solving the inverse design heat transfer problem of impingement cooling, providing a reliable model for generating data.

English

ISBN: 9798381021639Subjects--Topical Terms:

518875
Design.

Inverse Design and Optimization for Impingement Jet Cooling Using Variational Autoencoder /
LDR:02844nmm a22004333i 4500 001 2430386
005 20250519115954.5
006 m o d
007 cr|nu||||||||
008 261011s2023 miu||||||m |||||||eng d
020 $a 9798381021639
035 $a (MiAaPQD)AAI30727223
035 $a (MiAaPQD)NCState_Univ18402041245
035 $a AAI30727223
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Yannuwar, Sanket Vikrant, $e author. $3 3818674
245 1 0 $a Inverse Design and Optimization for Impingement Jet Cooling Using Variational Autoencoder / $c Sanket Vikrant Yannuwar.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 1 electronic resource (72 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 85-06.
500 $a Advisors: Yeh, Chi-An; Ekkad, Srinath V.; Yuan, Fuh-Gwo.
502 $b M.Sc. $c North Carolina State University $d 2023.
520 $a The focus of this study is to investigate the effectiveness of Variational Autoencoder (VAE) in solving the inverse design heat transfer problem of impingement cooling of a flat plate heat exchanger. Initially, data generation using Ansys Fluent was found to be computationally expensive and time-consuming. Therefore, I explored correlations developed from different research works on impingement cooling to save time and benchmark the application of VAE. The Florschuetz [1] correlation, which determines the impact of Reynolds number, array configuration, pitch to diameter ratio, and height to diameter ratio on crossflow and Nusselt number, was selected as these parameters have significant effects on the heat transfer and pressure drop. A dataset of 20,000 design points was generated, each having either 25 or 223 features that describe the design. Different VAE architectures were trained for inverse design, and the effects of various hyperparameters were explored. The testing loss was found to be within 5%. Additionally, the pressure drop due to crossflow was calculated, and a genetic algorithm was employed to determine the optimal design that generates the required Nusselt number while minimizing pressure drop. Overall, this study demonstrates the potential of VAEs in solving the inverse design heat transfer problem of impingement cooling, providing a reliable model for generating data.
546 $a English
590 $a School code: 0155
650 4 $a Design. $3 518875
650 4 $a Cooling. $3 1457878
650 4 $a Heat exchangers. $3 626398
650 4 $a Reynolds number. $3 3681436
650 4 $a Genetic algorithms. $3 533907
650 4 $a Fluid mechanics. $3 528155
650 4 $a Mechanics. $3 525881
650 4 $a Thermodynamics. $3 517304
690 $a 0389
690 $a 0800
690 $a 0204
690 $a 0346
690 $a 0348
710 2 $a North Carolina State University. $e degree granting institution. $3 3765716
720 1 $a Yeh, Chi-An $e degree supervisor.
720 1 $a Ekkad, Srinath V. $e degree supervisor.
720 1 $a Yuan, Fuh-Gwo $e degree supervisor.
773 0 $t Masters Abstracts International $g 85-06.
790 $a 0155
791 $a M.Sc.
792 $a 2023
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30727223