Micro‐phase separation kinetics of polyurethane nanocomposites with neural network

Thermoplastic polyurethane elastomers (TPUs) reinforced with multi wall carbon nanotubes (MWCNTs) and Closite30B, were prepared via melt mixing approach and investigated by spectroscopy, and rheological analyses. Following basic analyses, time sweep tests were used to determine the influence of temp...

Full description

Saved in:
Bibliographic Details
Published in:Polymer composites 2019-10, Vol.40 (10), p.3904-3913
Main Authors: Sahebi Jouibari, Iman, Haddadi‐Asl, Vahid, Ahmadi, Hanie, Mirhosseini, Mohammad Masoud
Format: Article
Language:English
Subjects:
Artificial neural networks
Aspect ratio
Kinetics
Multi wall carbon nanotubes
Nanocomposites
Neural networks
Phase separation
Polymers
Polyurethane resins
Rheological properties
Urethane thermoplastic elastomers
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Thermoplastic polyurethane elastomers (TPUs) reinforced with multi wall carbon nanotubes (MWCNTs) and Closite30B, were prepared via melt mixing approach and investigated by spectroscopy, and rheological analyses. Following basic analyses, time sweep tests were used to determine the influence of temperature, applied preshear and nanofiller content and aspect ratio on the micro‐phase separation kinetics of the nanocomposites. Based on the experimental results, artificial neural network was developed to explain the relationship between those parameters and micro‐phase separation time. The neural network is able to predict micro‐phase separation time of TPU nanocomposites possessing different nanofillers at various shear rates and temperatures. Comparison between experimental and calculated data by the model shows that the neural network can well‐communicate between input and target variables. POLYM. COMPOS., 40:3904–3913, 2019. © 2019 Society of Plastics Engineers
ISSN:0272-8397
1548-0569
DOI:10.1002/pc.25250