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

切換: 標籤 | MARC模式 | ISBD

Data-Driven Surrogate Models for Com...

Halder, Rakesh,

FindBook

Google Book

Amazon

博客來

Data-Driven Surrogate Models for Computational Fluid Dynamics /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Data-Driven Surrogate Models for Computational Fluid Dynamics // Rakesh Halder.
作者:	Halder, Rakesh,
面頁冊數:	1 electronic resource (159 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
Contained By:	Dissertations Abstracts International85-12B.
標題:	Applied mathematics. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31348865
ISBN:	9798382738307

Data-Driven Surrogate Models for Computational Fluid Dynamics /
Halder, Rakesh,

Data-Driven Surrogate Models for Computational Fluid Dynamics /Rakesh Halder. - 1 electronic resource (159 pages)

Source: Dissertations Abstracts International, Volume: 85-12, Section: B.

The use of computational fluid dynamics (CFD) has become essential for aerospace design optimization processes. The computational cost of high-fidelity CFD is often very large and can make design optimization prohibitively expensive if a large number of design evaluations are required. Reduced-order models (ROMs) are a method that can be used to mitigate this cost. ROMs are low-dimensional data-driven surrogate models that are trained using a set of computed high-fidelity simulation snapshots. Many ROMs utilize the proper orthogonal decomposition (POD), a linear subspace method for representing solution spaces. While ROMs are becoming increasingly popular, they do face some challenges in their practical use, which include maximizing accuracy for a given computational budget, the ability to generalize throughout a parameter space, and applicability to topologically dissimilar meshes.In this dissertation, algorithms are introduced to improve the performance, stability, and understanding of data-driven surrogate CFD models and their applications. As ROMs tend to use a small amount of training data, their predictive performance is highly sensitive to their choice. Algorithms to improve the data selection process for POD-based ROMs are introduced using Isomap, a versatile technique for nonlinear dimensionality reduction, resulting in significantly improved predictive performance for a given computational budget when used over a traditional and widely used statistical sampling technique. Next, ROMs using artificial neural networks, specifically convolutional autoencoders (CAEs), are introduced to address the performance limits of POD for problems that are highly nonlinear or require large amounts of training data, such as unsteady ROMs involving multiple designs. A steady ROM framework combining CAEs with Gaussian process regression (GPR) is introduced and shown to significantly outperform POD when applied to a highly nonlinear lid-driven cavity problem. Ensemble learning is also used to effectively address the issue of error propagation in unsteady ROMs, where errors made early on can accumulate and lead to large inaccuracies over long time horizons at unseen design points. Finally, field inversion and machine learning (FIML) is proposed as an an alternative to ROMs for problems that require topologically dissimilar meshes. Field inversion involves obtaining improvements to turbulence models by augmenting them with a corrective field that is obtained using gradient-based optimization. Using a machine learning model trained on local flow variables and their gradients, a data-driven turbulence model is introduced to improve the predictive capabilities of baseline turbulence models, allowing for the prediction of complex flow phenomena present in experimental results. 

English

ISBN: 9798382738307Subjects--Topical Terms:

2122814
Applied mathematics.
Subjects--Index Terms:

Nonlinear dimensionality reduction

Data-Driven Surrogate Models for Computational Fluid Dynamics /
LDR:04420nmm a22004813i 4500 001 2438618
005 20260727134402.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798382738307
035 $a (MiAaPQD)AAI31348865
035 $a (MiAaPQD)umichrackham005501
035 $a AAI31348865
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Halder, Rakesh, $e author. $3 3829981
245 1 0 $a Data-Driven Surrogate Models for Computational Fluid Dynamics / $c Rakesh Halder.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (159 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: 85-12, Section: B.
500 $a Advisors: Fidkowski, Krzysztof; Maki, Kevin Committee members: Collette, Matthew; Martins, Joaquim.
502 $b Ph.D. $c University of Michigan $d 2024.
520 $a The use of computational fluid dynamics (CFD) has become essential for aerospace design optimization processes. The computational cost of high-fidelity CFD is often very large and can make design optimization prohibitively expensive if a large number of design evaluations are required. Reduced-order models (ROMs) are a method that can be used to mitigate this cost. ROMs are low-dimensional data-driven surrogate models that are trained using a set of computed high-fidelity simulation snapshots. Many ROMs utilize the proper orthogonal decomposition (POD), a linear subspace method for representing solution spaces. While ROMs are becoming increasingly popular, they do face some challenges in their practical use, which include maximizing accuracy for a given computational budget, the ability to generalize throughout a parameter space, and applicability to topologically dissimilar meshes.In this dissertation, algorithms are introduced to improve the performance, stability, and understanding of data-driven surrogate CFD models and their applications. As ROMs tend to use a small amount of training data, their predictive performance is highly sensitive to their choice. Algorithms to improve the data selection process for POD-based ROMs are introduced using Isomap, a versatile technique for nonlinear dimensionality reduction, resulting in significantly improved predictive performance for a given computational budget when used over a traditional and widely used statistical sampling technique. Next, ROMs using artificial neural networks, specifically convolutional autoencoders (CAEs), are introduced to address the performance limits of POD for problems that are highly nonlinear or require large amounts of training data, such as unsteady ROMs involving multiple designs. A steady ROM framework combining CAEs with Gaussian process regression (GPR) is introduced and shown to significantly outperform POD when applied to a highly nonlinear lid-driven cavity problem. Ensemble learning is also used to effectively address the issue of error propagation in unsteady ROMs, where errors made early on can accumulate and lead to large inaccuracies over long time horizons at unseen design points. Finally, field inversion and machine learning (FIML) is proposed as an an alternative to ROMs for problems that require topologically dissimilar meshes. Field inversion involves obtaining improvements to turbulence models by augmenting them with a corrective field that is obtained using gradient-based optimization. Using a machine learning model trained on local flow variables and their gradients, a data-driven turbulence model is introduced to improve the predictive capabilities of baseline turbulence models, allowing for the prediction of complex flow phenomena present in experimental results. 
546 $a English
590 $a School code: 0127
650 4 $a Applied mathematics. $3 2122814
650 4 $a Computer science. $3 523869
650 4 $a Aerospace engineering. $3 1002622
650 4 $a Fluid mechanics. $3 528155
653 $a Nonlinear dimensionality reduction
653 $a Computational fluid dynamics
653 $a Machine learning
653 $a Surrogate modeling
653 $a Deep learning
690 $a 0538
690 $a 0364
690 $a 0984
690 $a 0800
690 $a 0204
710 2 $a University of Michigan. $b Aerospace Engineering. $e degree granting institution. $3 3817051
720 1 $a Fidkowski, Krzysztof $e degree supervisor.
720 1 $a Maki, Kevin $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 85-12B.
790 $a 0127
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31348865