Loading [MathJax]/extensions/tex2jax.js

Deep learning informed multiphysics material modeling of fiber reinforced polymer nanocomposites

Research output: Thesis › Doctoral thesis

Authors

  • Betim Bahtiri

Research Organisations

Details

Original languageEnglish
QualificationDoctor of Engineering
Awarding Institution
Supervised by
Date of Award5 Nov 2024
Place of PublicationHannover
Publication statusPublished - 13 Nov 2024

Abstract

The development of high-performance fiber-reinforced polymer nanocomposites is a major focus in the field of lightweight materials for engineering applications due to their improved mechanical properties. However, the complex interactions between nanoparticles, fibers, and polymeric matrices pose a significant challenge in accurately and comprehensively understanding the multiphysics behavior of the nanocomposites, which is essential for reliably developing material models. The thesis at hand contributes to this challenge by providing an enhanced and deep learning-informed framework for multiphysics material modeling of fiber-reinforced polymer nanocomposites, combining molecular simulations, nonlinear finite element simulations, and deep learning techniques. The framework is designed to capture the intricate structure-property relationships of these materials, including the effects of moisture, temperature, and nanoparticle incorporation on material behavior.

Cite this

Deep learning informed multiphysics material modeling of fiber reinforced polymer nanocomposites. / Bahtiri, Betim.
Hannover, 2024. 122 p.

Research output: Thesis › Doctoral thesis

Bahtiri, B 2024, 'Deep learning informed multiphysics material modeling of fiber reinforced polymer nanocomposites', Doctor of Engineering, Leibniz University Hannover, Hannover. https://doi.org/10.15488/18108
Download
@phdthesis{1bc292a1818d4ce2afd826446bcb4f90,
title = "Deep learning informed multiphysics material modeling of fiber reinforced polymer nanocomposites",
abstract = "The development of high-performance fiber-reinforced polymer nanocomposites is a major focus in the field of lightweight materials for engineering applications due to their improved mechanical properties. However, the complex interactions between nanoparticles, fibers, and polymeric matrices pose a significant challenge in accurately and comprehensively understanding the multiphysics behavior of the nanocomposites, which is essential for reliably developing material models. The thesis at hand contributes to this challenge by providing an enhanced and deep learning-informed framework for multiphysics material modeling of fiber-reinforced polymer nanocomposites, combining molecular simulations, nonlinear finite element simulations, and deep learning techniques. The framework is designed to capture the intricate structure-property relationships of these materials, including the effects of moisture, temperature, and nanoparticle incorporation on material behavior.",
author = "Betim Bahtiri",
year = "2024",
month = nov,
day = "13",
doi = "10.15488/18108",
language = "English",
school = "Leibniz University Hannover",

}

Download

TY - BOOK

T1 - Deep learning informed multiphysics material modeling of fiber reinforced polymer nanocomposites

AU - Bahtiri, Betim

PY - 2024/11/13

Y1 - 2024/11/13

N2 - The development of high-performance fiber-reinforced polymer nanocomposites is a major focus in the field of lightweight materials for engineering applications due to their improved mechanical properties. However, the complex interactions between nanoparticles, fibers, and polymeric matrices pose a significant challenge in accurately and comprehensively understanding the multiphysics behavior of the nanocomposites, which is essential for reliably developing material models. The thesis at hand contributes to this challenge by providing an enhanced and deep learning-informed framework for multiphysics material modeling of fiber-reinforced polymer nanocomposites, combining molecular simulations, nonlinear finite element simulations, and deep learning techniques. The framework is designed to capture the intricate structure-property relationships of these materials, including the effects of moisture, temperature, and nanoparticle incorporation on material behavior.

AB - The development of high-performance fiber-reinforced polymer nanocomposites is a major focus in the field of lightweight materials for engineering applications due to their improved mechanical properties. However, the complex interactions between nanoparticles, fibers, and polymeric matrices pose a significant challenge in accurately and comprehensively understanding the multiphysics behavior of the nanocomposites, which is essential for reliably developing material models. The thesis at hand contributes to this challenge by providing an enhanced and deep learning-informed framework for multiphysics material modeling of fiber-reinforced polymer nanocomposites, combining molecular simulations, nonlinear finite element simulations, and deep learning techniques. The framework is designed to capture the intricate structure-property relationships of these materials, including the effects of moisture, temperature, and nanoparticle incorporation on material behavior.

U2 - 10.15488/18108

DO - 10.15488/18108

M3 - Doctoral thesis

CY - Hannover

ER -

By the same author(s)