Application of Machine Learning Tools for the Improvement of Reactive Extrusion Simulation

The purpose of this paper is to combine a classical 1D twin‐screw extrusion model with machine learning techniques to obtain accurate predictions of a complex system despite few data. Systems involving reactive polyethylene oligomer dispersed in situ in a polypropylene matrix by reactive twin‐screw...

Full description

Saved in:
Bibliographic Details
Published inMacromolecular materials and engineering Vol. 305; no. 12
Main Authors Castéran, Fanny, Ibanez, Ruben, Argerich, Clara, Delage, Karim, Chinesta, Francisco, Cassagnau, Philippe
Format Journal Article
LanguageEnglish
Published Weinheim John Wiley & Sons, Inc 01.12.2020
Wiley-VCH Verlag
Subjects
artificial engineering
Complex systems
Engineering Sciences
experimental data
Extrusion
Machine learning
Materials
Polyethylenes
polymer processing
reactive extrusion
Simulation
polymer processing
reactive extrusion
artificial engineering
machine learning
experimental data
Online AccessGet full text

Cover

More Information
Summary:The purpose of this paper is to combine a classical 1D twin‐screw extrusion model with machine learning techniques to obtain accurate predictions of a complex system despite few data. Systems involving reactive polyethylene oligomer dispersed in situ in a polypropylene matrix by reactive twin‐screw extrusion are studied for this purpose. The twin‐screw extrusion simulation software LUDOVIC is used and machine learning techniques dealing with low data limit are used as a correction of the simulation. Dispersion of reactive polyethylene oligomer networks in a polyethylene matrix is performed by twin‐screw extrusion and characterized. A 1D twin‐screw extrusion simulation software is used and compared to the experimental results. Machine learning techniques dealing with low data limit are then used to create a correction of the simulation and obtain a better predictive model.
ISSN:1438-7492
1439-2054
DOI:10.1002/mame.202000375