國立虎尾科技大學 |

Integrated Machine Learning and Computational Framework for Predicting the Thermophysical and Functional Properties of Polymers.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Integrated Machine Learning and Computational Framework for Predicting the Thermophysical and Functional Properties of Polymers./
Author:	Karuthedathkuzhiyil, Anas.
Description:	1 online resource (174 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
Contained By:	Dissertations Abstracts International84-12B.
Subject:	Polymer chemistry. -
Online resource:	click for full text (PQDT)
ISBN:	9798379594572

Integrated Machine Learning and Computational Framework for Predicting the Thermophysical and Functional Properties of Polymers.
Karuthedathkuzhiyil, Anas.

Integrated Machine Learning and Computational Framework for Predicting the Thermophysical and Functional Properties of Polymers. - 1 online resource (174 pages)

Source: Dissertations Abstracts International, Volume: 84-12, Section: B.

Thesis (Ph.D.)--North Dakota State University, 2023.

Includes bibliographical references

Accelerating the pace of discovery and deployment of advanced polymeric materials is crucial for achieving global competitiveness. The fast-track development of polymeric materials requires new fundamental knowledge of structure-property-morphology relationships to predict, control, and manipulate the thermophysical and functional properties. The synergistic framework obtained by integrating data-driven machine learning (ML) and multiscale molecular modeling (MD) methods can provide molecular level insights into the thermophysical and functional properties of polymeric materials. This dissertation aims to employ data-driven ML methods in tandem with multiscale molecular modeling to gain deeper insights into glass transition temperature (Tg), hygrothermal degradation mechanism, and fouling release (FR) properties of polymeric materials. In a first study, the integrated framework by combining data-driven ML methods and coarse-grained (CG)-MD simulations are used to identify the key structural and functional attributes that govern the Tg of polymers. Informed by the ML model, CG-MD simulations are performed to further delineate mechanistic interpretation and systematic dependence of these influential molecular features on Tg by investigating three major CG model parameters, namely the cohesive interaction chain stiffness, and grafting density. In another study, the reactive molecular dynamics (ReaxFF) is applied to gain a molecular-level understanding of the hygrothermal degradation of crosslinked epoxy polymers. We believe our results provide new insights into the reversible and irreversible hygrothermal aging process in the epoxy network and inform us about the new design criteria for broadening the application of epoxy materials, particularly in humid environments. Next, an innovative modeling framework is developed by integrating machine learning (ML), statistical thermodynamics, molecular dynamics simulations, and surface characterization techniques to gain deeper insights into the fouling release (FR) mechanism of phenylmethyl silicone oil modified PDMS based coatings. We believe the synergetic framework established in this dissertation work by combining data-driven ML techniques and multiscale molecular modeling methods is important milestone in the methodology development to design and perform structure-property predictions of polymers, paving the way for accelerated discovery and deployment of polymeric materials for multifunctional applications.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798379594572Subjects--Topical Terms:

1182163
Polymer chemistry.
Subjects--Index Terms:

Machine learningIndex Terms--Genre/Form:

554714
Electronic books.

Integrated Machine Learning and Computational Framework for Predicting the Thermophysical and Functional Properties of Polymers.
LDR:03949ntm a22003977 4500 001 1144250
005 20240531083810.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798379594572
035 $a (MiAaPQ)AAI30250144
035 $a AAI30250144
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Karuthedathkuzhiyil, Anas. $3 1469214
245 1 0 $a Integrated Machine Learning and Computational Framework for Predicting the Thermophysical and Functional Properties of Polymers.
264 0 $c 2023
300 $a 1 online resource (174 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: 84-12, Section: B.
500 $a Advisor: Rasulev, Bakhtiyor.
502 $a Thesis (Ph.D.)--North Dakota State University, 2023.
504 $a Includes bibliographical references
520 $a Accelerating the pace of discovery and deployment of advanced polymeric materials is crucial for achieving global competitiveness. The fast-track development of polymeric materials requires new fundamental knowledge of structure-property-morphology relationships to predict, control, and manipulate the thermophysical and functional properties. The synergistic framework obtained by integrating data-driven machine learning (ML) and multiscale molecular modeling (MD) methods can provide molecular level insights into the thermophysical and functional properties of polymeric materials. This dissertation aims to employ data-driven ML methods in tandem with multiscale molecular modeling to gain deeper insights into glass transition temperature (Tg), hygrothermal degradation mechanism, and fouling release (FR) properties of polymeric materials. In a first study, the integrated framework by combining data-driven ML methods and coarse-grained (CG)-MD simulations are used to identify the key structural and functional attributes that govern the Tg of polymers. Informed by the ML model, CG-MD simulations are performed to further delineate mechanistic interpretation and systematic dependence of these influential molecular features on Tg by investigating three major CG model parameters, namely the cohesive interaction chain stiffness, and grafting density. In another study, the reactive molecular dynamics (ReaxFF) is applied to gain a molecular-level understanding of the hygrothermal degradation of crosslinked epoxy polymers. We believe our results provide new insights into the reversible and irreversible hygrothermal aging process in the epoxy network and inform us about the new design criteria for broadening the application of epoxy materials, particularly in humid environments. Next, an innovative modeling framework is developed by integrating machine learning (ML), statistical thermodynamics, molecular dynamics simulations, and surface characterization techniques to gain deeper insights into the fouling release (FR) mechanism of phenylmethyl silicone oil modified PDMS based coatings. We believe the synergetic framework established in this dissertation work by combining data-driven ML techniques and multiscale molecular modeling methods is important milestone in the methodology development to design and perform structure-property predictions of polymers, paving the way for accelerated discovery and deployment of polymeric materials for multifunctional applications.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Polymer chemistry. $3 1182163
650 4 $a Thermodynamics. $3 596513
653 $a Machine learning
653 $a Multiscale modeling
653 $a Polymeric materials
653 $a Epoxy polymers
653 $a Multifunctional applications
655 7 $a Electronic books. $2 local $3 554714
690 $a 0495
690 $a 0800
690 $a 0348
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a North Dakota State University. $b Coatings and Polymeric Materials. $3 1469215
773 0 $t Dissertations Abstracts International $g 84-12B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30250144 $z click for full text (PQDT)