A Neural Network Approach to Processing Photos of Carbon-Fiber-Reinforced Polymer Microstructures for Their Further Diagnostics

A neural network approach to the segmentation of photos for carbon fiber reinforced polymer structures with the purpose of qualitative and quantitative fault analysis was considered. The object of study was carbon-fiber-reinforced polymer (CFRP) based on an epoxy binder. Such a composite material wa...

Full description

Saved in:
Bibliographic Details
Published in:Polymer science. Series D, Glues and sealing materials Glues and sealing materials, 2023-06, Vol.16 (2), p.307-312
Main Authors: Tikhonova, D. S., Abramochkin, A. Yu, Borodulin, A. S., Nelyub, V. A., Malysheva, G. V.
Format: Article
Language:English
Subjects:
Carbon fiber reinforced plastics
Chemistry
Chemistry and Materials Science
Composite materials
Fiber reinforced polymers
Microstructure
Neural networks
Polymer Sciences
Qualitative analysis
Segmentation
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A neural network approach to the segmentation of photos for carbon fiber reinforced polymer structures with the purpose of qualitative and quantitative fault analysis was considered. The object of study was carbon-fiber-reinforced polymer (CFRP) based on an epoxy binder. Such a composite material was molded with an organosilicon sealant additive, which acted as a “liquid” matrix. A method of formalizing the microstructure photo segmentation problem and a method of training a neural network were presented.
ISSN:1995-4212
1995-4220
DOI:10.1134/S1995421223020442