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

Geometry-Informed Data-Driven Mechan...

Bahmani, Bahador,

FindBook

Google Book

Amazon

博客來

Geometry-Informed Data-Driven Mechanics /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Geometry-Informed Data-Driven Mechanics // Bahador Bahmani.
作者:	Bahmani, Bahador,
面頁冊數:	1 electronic resource (385 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-07, Section: B.
Contained By:	Dissertations Abstracts International85-07B.
標題:	Computational physics. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30988049
ISBN:	9798381431285

Geometry-Informed Data-Driven Mechanics /
Bahmani, Bahador,

Geometry-Informed Data-Driven Mechanics /Bahador Bahmani. - 1 electronic resource (385 pages)

Source: Dissertations Abstracts International, Volume: 85-07, Section: B.

Computer simulations for civil and mechanical engineering that efficiently leverage computational resources to solve boundary value problems have pervasive impacts on many aspects of civilization, including manufacturing, communication, transportation, medicine, and defense. Conventionally, a solver that predicts the mechanical behaviors of solids requires constitutive laws that represent mechanisms not directly derived from balance principles. These mechanisms are often characterized by mathematical models validated and tested via tabulated data, organized in grids or, more broadly, within normed Euclidean space (e.g., principle stress space, Mohr circle). These mathematical models often involved mapping between/among normed vector spaces that adhere to physical constraints. This methodology has manifested frameworks such as hyperelastic energy functional, elastoplasticity models with evolving internal variables, cohesive zone models for fracture, etc. However, the geometry of material data plays a crucial role in the efficiency, accuracy, and robustness of predictions.This thesis introduces a collection of mathematical models, tools, algorithms, and frameworks that, when integrated, may unleash the potential of leveraging data geometry to advance solid mechanics modeling. In the first part of the thesis, we introduce the concept of treating constitutive data as a manifold. This idea leads to a novel data-driven paradigm called "Manifold Embedding Data-Driven Mechanics," which incorporates the manifold structure of data into the distance minimization model-free method. By training an invertible artificial neural network (ANN) to embed nonlinear constitutive data onto a hyperplane, we replace the costly combinatoric optimization necessary for the classical model-free paradigm with a projection and, as a result, significantly improve the efficiency and robustness of the model-free approach with a distance measure consistent with the data geometry. This method facilitates consistent interpolation on the manifold, which improves the accuracy when data is limited. To handle noisy data, we relax the invertibility constraint of the designed ANN and construct the desired embedding space via a geometric autoencoder. Unlike the classical autoencoder, which compresses data by reducing the data dimensionality in the latent space, our design focuses on reducing the dimensionality of the data by imposing constraints. This technique enables us to learn a noise-free embedding through a simple projection by assuming the orthogonality between the data and noise.To improve the interpretability and, ultimately, the trustworthiness of machine learning-derived constitutive models, we abandon the design of the fully connected neural networks and instead introduce polynomials in feature space that enable us to turn neural network parametrized black-box models back into mathematical models understandable by engineers. We present geometrically inspired structures in a feature space spanned by univariate ANNs and then learn a sparse representation of the data using these acquired features. Our divide-and-conquer scheme takes advantage of the learned univariate functions to perform parallel symbolic regression, ultimately extracting human-readable equations for material modeling. Our approach mitigates the well-known computational burden associated with symbolic regression for high-dimensional data and data that must adhere to physical constraints. We demonstrate the interpretability, accuracy, and computational efficiency of our algorithm in discovering constitutive models for hyperelastic materials and plastic yield surfaces.

English

ISBN: 9798381431285Subjects--Topical Terms:

3343998
Computational physics.
Subjects--Index Terms:

Elastoplasticity

Geometry-Informed Data-Driven Mechanics /
LDR:05019nmm a22004453i 4500 001 2432347
005 20250707081445.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798381431285
035 $a (MiAaPQD)AAI30988049
035 $a AAI30988049
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Bahmani, Bahador, $e author. $3 3821527
245 1 0 $a Geometry-Informed Data-Driven Mechanics / $c Bahador Bahmani.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (385 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: 85-07, Section: B.
500 $a Advisors: Sun, WaiChing.
502 $b Ph.D. $c Columbia University $d 2024.
520 $a Computer simulations for civil and mechanical engineering that efficiently leverage computational resources to solve boundary value problems have pervasive impacts on many aspects of civilization, including manufacturing, communication, transportation, medicine, and defense. Conventionally, a solver that predicts the mechanical behaviors of solids requires constitutive laws that represent mechanisms not directly derived from balance principles. These mechanisms are often characterized by mathematical models validated and tested via tabulated data, organized in grids or, more broadly, within normed Euclidean space (e.g., principle stress space, Mohr circle). These mathematical models often involved mapping between/among normed vector spaces that adhere to physical constraints. This methodology has manifested frameworks such as hyperelastic energy functional, elastoplasticity models with evolving internal variables, cohesive zone models for fracture, etc. However, the geometry of material data plays a crucial role in the efficiency, accuracy, and robustness of predictions.This thesis introduces a collection of mathematical models, tools, algorithms, and frameworks that, when integrated, may unleash the potential of leveraging data geometry to advance solid mechanics modeling. In the first part of the thesis, we introduce the concept of treating constitutive data as a manifold. This idea leads to a novel data-driven paradigm called "Manifold Embedding Data-Driven Mechanics," which incorporates the manifold structure of data into the distance minimization model-free method. By training an invertible artificial neural network (ANN) to embed nonlinear constitutive data onto a hyperplane, we replace the costly combinatoric optimization necessary for the classical model-free paradigm with a projection and, as a result, significantly improve the efficiency and robustness of the model-free approach with a distance measure consistent with the data geometry. This method facilitates consistent interpolation on the manifold, which improves the accuracy when data is limited. To handle noisy data, we relax the invertibility constraint of the designed ANN and construct the desired embedding space via a geometric autoencoder. Unlike the classical autoencoder, which compresses data by reducing the data dimensionality in the latent space, our design focuses on reducing the dimensionality of the data by imposing constraints. This technique enables us to learn a noise-free embedding through a simple projection by assuming the orthogonality between the data and noise.To improve the interpretability and, ultimately, the trustworthiness of machine learning-derived constitutive models, we abandon the design of the fully connected neural networks and instead introduce polynomials in feature space that enable us to turn neural network parametrized black-box models back into mathematical models understandable by engineers. We present geometrically inspired structures in a feature space spanned by univariate ANNs and then learn a sparse representation of the data using these acquired features. Our divide-and-conquer scheme takes advantage of the learned univariate functions to perform parallel symbolic regression, ultimately extracting human-readable equations for material modeling. Our approach mitigates the well-known computational burden associated with symbolic regression for high-dimensional data and data that must adhere to physical constraints. We demonstrate the interpretability, accuracy, and computational efficiency of our algorithm in discovering constitutive models for hyperelastic materials and plastic yield surfaces.
546 $a English
590 $a School code: 0054
650 4 $a Computational physics. $3 3343998
650 4 $a Mechanics. $3 525881
650 4 $a Mechanical engineering. $3 649730
653 $a Elastoplasticity
653 $a Civilization
653 $a Computer simulations
653 $a Mathematical models
653 $a Robustness
690 $a 0543
690 $a 0216
690 $a 0346
690 $a 0548
710 2 $a Columbia University. $b Civil Engineering and Engineering Mechanics. $e degree granting institution. $3 3815978
720 1 $a Sun, WaiChing $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 85-07B.
790 $a 0054
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30988049