東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

Developing Machine-Learning Algorith...

Zhang, Zexia,

FindBook

Google Book

Amazon

博客來

Developing Machine-Learning Algorithms for Predicting Turbulent Flows in Large-Scale Waterways, Oceanic Environments, and Utility-Scale Wind Farms /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Developing Machine-Learning Algorithms for Predicting Turbulent Flows in Large-Scale Waterways, Oceanic Environments, and Utility-Scale Wind Farms // Zexia Zhang.
作者:	Zhang, Zexia,
面頁冊數:	1 electronic resource (211 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-05, Section: B.
Contained By:	Dissertations Abstracts International86-05B.
標題:	Mechanical engineering. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31556907
ISBN:	9798342728379

Developing Machine-Learning Algorithms for Predicting Turbulent Flows in Large-Scale Waterways, Oceanic Environments, and Utility-Scale Wind Farms /
Zhang, Zexia,

Developing Machine-Learning Algorithms for Predicting Turbulent Flows in Large-Scale Waterways, Oceanic Environments, and Utility-Scale Wind Farms /Zexia Zhang. - 1 electronic resource (211 pages)

Source: Dissertations Abstracts International, Volume: 86-05, Section: B.

Accurately predicting turbulent flow is critical for infrastructure design, operation, and risk assessment in engineering. For example, in wind farms, the power production of wind turbines is affected by atmospheric stability and wake overlapping. Turbulent river flows can undermine the foundation of hydraulic structures and change the morphology of meandering rivers. Thus, accurate prediction of turbulent flows can help prevent drawbacks and utilize advantages in engineering practices. However, the conventional high-fidelity computational fluid dynamics (CFD) prediction approach, such as large eddy simulation (LES), is computationally expensive for resolving high-Reynolds turbulent flows in wind farms and natural waterways due to the high demands for computational grid nodes in large-scale flow domains and the long sampling time required to calculate the turbulence statistics.This thesis proposes a machine learning (ML)-based framework that has the potential to significantly impact the field of engineering. It augments the efficiency of LES in predicting turbulence statistics, such as mean velocity fields and turbulence kinetic energy, with high accuracy. Specifically, the proposed ML algorithm uses instantaneous snapshots of LES to predict turbulence statistics, reducing the computational resource demands of LES by over 80% for generating statistical samples. The efficiency, accuracy, and generality of the proposed ML algorithm are widely validated for the prediction of (a) the turbulent flow of large-scale rivers with wall-mounted bridge piers and marine hydrokinetic turbines, (b) bed deformation of large-scale meandering rivers, (c) ocean wave-wind interactions, and (d) turbine wake flows in utility-scale wind farms, demonstrating its capability in various engineering applications.

English

ISBN: 9798342728379Subjects--Topical Terms:

649730
Mechanical engineering.
Subjects--Index Terms:

Turbulence statistics

Developing Machine-Learning Algorithms for Predicting Turbulent Flows in Large-Scale Waterways, Oceanic Environments, and Utility-Scale Wind Farms /
LDR:03469nmm a22004573i 4500 001 2438665
005 20260727134407.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798342728379
035 $a (MiAaPQD)AAI31556907
035 $a AAI31556907
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Zhang, Zexia, $e author. $3 3830036
245 1 0 $a Developing Machine-Learning Algorithms for Predicting Turbulent Flows in Large-Scale Waterways, Oceanic Environments, and Utility-Scale Wind Farms / $c Zexia Zhang.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (211 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: Dissertations Abstracts International, Volume: 86-05, Section: B.
500 $a Advisors: Burgueño, Rigoberto; Khosronejad, Ali Committee members: Farhadzadeh, Ali; Sotiropoulos, Fotis.
502 $b Ph.D. $c State University of New York at Stony Brook $d 2024.
520 $a Accurately predicting turbulent flow is critical for infrastructure design, operation, and risk assessment in engineering. For example, in wind farms, the power production of wind turbines is affected by atmospheric stability and wake overlapping. Turbulent river flows can undermine the foundation of hydraulic structures and change the morphology of meandering rivers. Thus, accurate prediction of turbulent flows can help prevent drawbacks and utilize advantages in engineering practices. However, the conventional high-fidelity computational fluid dynamics (CFD) prediction approach, such as large eddy simulation (LES), is computationally expensive for resolving high-Reynolds turbulent flows in wind farms and natural waterways due to the high demands for computational grid nodes in large-scale flow domains and the long sampling time required to calculate the turbulence statistics.This thesis proposes a machine learning (ML)-based framework that has the potential to significantly impact the field of engineering. It augments the efficiency of LES in predicting turbulence statistics, such as mean velocity fields and turbulence kinetic energy, with high accuracy. Specifically, the proposed ML algorithm uses instantaneous snapshots of LES to predict turbulence statistics, reducing the computational resource demands of LES by over 80% for generating statistical samples. The efficiency, accuracy, and generality of the proposed ML algorithm are widely validated for the prediction of (a) the turbulent flow of large-scale rivers with wall-mounted bridge piers and marine hydrokinetic turbines, (b) bed deformation of large-scale meandering rivers, (c) ocean wave-wind interactions, and (d) turbine wake flows in utility-scale wind farms, demonstrating its capability in various engineering applications.
546 $a English
590 $a School code: 0771
650 4 $a Mechanical engineering. $3 649730
650 4 $a Computer science. $3 523869
650 4 $a Fluid mechanics. $3 528155
653 $a Turbulence statistics
653 $a Computational fluid dynamics
653 $a Machine learning
653 $a Large eddy simulation
653 $a Turbulent river flows
690 $a 0543
690 $a 0548
690 $a 0984
690 $a 0204
710 2 $a State University of New York at Stony Brook. $b Civil Engineering. $e degree granting institution. $3 3830037
720 1 $a Burgueño, Rigoberto $e degree supervisor.
720 1 $a Khosronejad, Ali $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-05B.
790 $a 0771
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31556907