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

Machine Learning with Hard Constrain...

Tac, Vahidullah,

Linked to FindBook

Google Book

Amazon

博客來

Machine Learning with Hard Constraints:physics-constrained Constitutive Models with Neural odes and Diffusion /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Machine Learning with Hard Constraints:physics-constrained Constitutive Models with Neural odes and Diffusion // Vahidullah Tac.
Author:	Tac, Vahidullah,
Description:	1 electronic resource (261 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-04, Section: B.
Contained By:	Dissertations Abstracts International86-04B.
Subject:	Physics. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31532253
ISBN:	9798342130660

Machine Learning with Hard Constraints:physics-constrained Constitutive Models with Neural odes and Diffusion /
Tac, Vahidullah,

Machine Learning with Hard Constraints:physics-constrained Constitutive Models with Neural odes and Diffusion /Vahidullah Tac. - 1 electronic resource (261 pages)

Source: Dissertations Abstracts International, Volume: 86-04, Section: B.

Our current constitutive models of material behavior fall short of being able to describe the mechanics of soft tissues. This is because soft tissues like skin and rubber, unlike traditional engineering materials, exhibit extremely nonlinear mechanical behavior and usually undergo large deformations. Developing accurate constitutive models for such materials requires using flexible tools at the forefront of science, such as machine learning methods. However, our past experiences show that it is crucial to incorporate physical knowledge in models of physical phenomena. The past few years has witnessed the rise of physics-informed models where the goal is to impose governing physical laws by incorporating them in the loss function. However, we argue that such "soft" constraints are not enough. This "persuasion" method has no theoretical guarantees on the satisfaction of physics and result in overly complicated loss functions that make training of the models cumbersome.We propose imposing the relevant physical laws as "hard" constraints. In this approach the physics of the problem are "baked in" into the structure of the model preventing it from ever violating them. We demonstrate the power of this paradigm on a number of constitutive models of soft tissue, including hyperelasticity, viscoelasticity and continuum damage models.We also argue that new uncertainty quantification strategies have to be developed to address the rise in dimensionality and the inherent symmetries present in most machine learning models compared to traditional constitutive models. We demonstrate that diffusion models can be used to construct a generative framework for physics-constrained hyperelastic constitutive models.

English

ISBN: 9798342130660Subjects--Topical Terms:

516296
Physics.

Machine Learning with Hard Constraints:physics-constrained Constitutive Models with Neural odes and Diffusion /
LDR:03303nmm a22004453i 4500 001 2429383
005 20250430100814.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798342130660
035 $a (MiAaPQD)AAI31532253
035 $a (MiAaPQD)Purdue26305066
035 $a AAI31532253
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Tac, Vahidullah, $e author. $3 3817201
245 1 0 $a Machine Learning with Hard Constraints:physics-constrained Constitutive Models with Neural odes and Diffusion / $c Vahidullah Tac.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (261 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: 86-04, Section: B.
500 $a Advisors: Tepole, Adrian Buganza; Bilionis, Ilias; Costabal, Francisco Sahli; Jahanshahi, Mohammad Reza.
502 $b Ph.D. $c Purdue University $d 2024.
520 $a Our current constitutive models of material behavior fall short of being able to describe the mechanics of soft tissues. This is because soft tissues like skin and rubber, unlike traditional engineering materials, exhibit extremely nonlinear mechanical behavior and usually undergo large deformations. Developing accurate constitutive models for such materials requires using flexible tools at the forefront of science, such as machine learning methods. However, our past experiences show that it is crucial to incorporate physical knowledge in models of physical phenomena. The past few years has witnessed the rise of physics-informed models where the goal is to impose governing physical laws by incorporating them in the loss function. However, we argue that such "soft" constraints are not enough. This "persuasion" method has no theoretical guarantees on the satisfaction of physics and result in overly complicated loss functions that make training of the models cumbersome.We propose imposing the relevant physical laws as "hard" constraints. In this approach the physics of the problem are "baked in" into the structure of the model preventing it from ever violating them. We demonstrate the power of this paradigm on a number of constitutive models of soft tissue, including hyperelasticity, viscoelasticity and continuum damage models.We also argue that new uncertainty quantification strategies have to be developed to address the rise in dimensionality and the inherent symmetries present in most machine learning models compared to traditional constitutive models. We demonstrate that diffusion models can be used to construct a generative framework for physics-constrained hyperelastic constitutive models.
546 $a English
590 $a School code: 0183
650 4 $a Physics. $3 516296
650 4 $a Tissues. $3 608294
650 4 $a Viscoelasticity. $3 718183
650 4 $a Ordinary differential equations. $3 3563004
650 4 $a Neural networks. $3 677449
650 4 $a Materials science. $3 543314
650 4 $a Mathematics. $3 515831
650 4 $a Mechanics. $3 525881
690 $a 0605
690 $a 0800
690 $a 0794
690 $a 0405
690 $a 0346
710 2 $a Purdue University. $e degree granting institution. $3 3759105
720 1 $a Tepole, Adrian Buganza $e degree supervisor.
720 1 $a Bilionis, Ilias $e degree supervisor.
720 1 $a Costabal, Francisco Sahli $e degree supervisor.
720 1 $a Jahanshahi, Mohammad Reza $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-04B.
790 $a 0183
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31532253