Titre :

Intelligent Machine Learning: Tailor-Making Macromolecules

Auteur(s) :

Mohammadi, Yousef [Auteur]
Saeb, Mohammad Reza [Auteur]
Institute for Color Science and Technology
Penlidis, Alexander [Auteur]
Department of Chemical Engineering [Waterloo]
Jabbari, Esmaiel [Auteur]
Department of Chemical Engineering [Columbia]
Stadler, Florian J. [Auteur]
Shenzhen University [Shenzhen]
Zinck, Philippe [Auteur]
Unité de Catalyse et Chimie du Solide (UCCS) - UMR 8181
Unité de Catalyse et Chimie du Solide - UMR 8181 [UCCS]
Matyjaszewski, Krzysztof [Auteur]
Carnegie Mellon University [Pittsburgh] [CMU]

Titre de la revue :

Polymers

Numéro :

11

Pagination :

579-592

Date de publication :

2019

Mot(s)-clé(s) en anglais :

microstructure
Kinetic Monte Carlo
living copolymerization
olefin block copolymers
artificial intelligence
ethylene
machine learning
genetic algorithms

Discipline(s) HAL :

Chimie/Catalyse

Résumé en anglais : [en]

Nowadays, polymer reaction engineers seek robust and effective tools to synthesizecomplex macromolecules with well-defined and desirable microstructural and architecturalcharacteristics. Over the past few ...
Lire la suite >Nowadays, polymer reaction engineers seek robust and effective tools to synthesizecomplex macromolecules with well-defined and desirable microstructural and architecturalcharacteristics. Over the past few decades, several promising approaches, such as controlled living(co)polymerization systems and chain-shuttling reactions have been proposed and widely applied tosynthesize rather complex macromolecules with controlled monomer sequences. Despite the uniquepotential of the newly developed techniques, tailor-making the microstructure of macromolecules bysuggesting the most appropriate polymerization recipe still remains a very challenging task. In thecurrent work, two versatile and powerful tools capable of effectively addressing the aforementionedquestions have been proposed and successfully put into practice. The two tools are establishedthrough the amalgamation of the Kinetic Monte Carlo simulation approach and machine learningtechniques. The former, an intelligent modeling tool, is able to model and visualize the intricateinter-relationships of polymerization recipes/conditions (as input variables) and microstructuralfeatures of the produced macromolecules (as responses). The latter is capable of precisely predictingoptimal copolymerization conditions to simultaneously satisfy all predefined microstructural features.The effectiveness of the proposed intelligent modeling and optimization techniques for solving thisextremely important ‘inverse’ engineering problem was successfully examined by investigatingthe possibility of tailor-making the microstructure of Olefin Block Copolymers via chain-shuttlingcoordination polymerization.Lire moins >

Langue :

Anglais

Audience :

Internationale

Vulgarisation :

Non

Établissement(s) :

ENSCL
CNRS
Centrale Lille
Univ. Artois
Université de Lille

Collections :

• Unité de Catalyse et Chimie du Solide (UCCS) - UMR 8181

Équipe(s) de recherche :

Catalyse et synthèse éco-compatible (CASECO)

Date de dépôt :

2019-09-25T15:07:16Z
2020-12-03T14:49:59Z