Back to Search Start Over

An integrated texture analysis and machine learning approach for durability assessment of lightweight cement composites with hydrophobic coatings modified by nanocellulose.

Authors :
Barnat-Hunek, Danuta
Omiotek, Zbigniew
Szafraniec, Małgorzata
Dzierżak, Róża
Source :
Measurement (02632241). Jul2021, Vol. 179, pN.PAG-N.PAG. 1p.
Publication Year :
2021

Abstract

• Texture parameters of the composites contain the information about their durability. • Machine learning algorithms used for the assessment of hydrophobization efficiency. • Microstructural properties of hydrophobic coatings modified by nanocellulose. The aim of the study was to determine a set of image texture features of the lightweight cementitious composites (LLC) with hydrophobic coatings modified with nanocellulose and use them to assess the materials' durability. A novel method based on a combination of image texture analysis and machine learning methods was proposed. Textural features were extracted from the images obtained with a scanning microscope. The best classification model was built by the Support Vector Machine method using 16 features selected by the Sequential Forward Selection algorithm. The model recognizes one of the four ranges of the contact angle, which is closely related to the degree of resistance of the analyzed material, with an accuracy of 82%. The results obtained show a relationship between the effectiveness of hydrophobic coatings in LCC and images of their surfaces. This relationship can be used with machine learning methods for conducting strength diagnostics of building materials. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
02632241
Volume :
179
Database :
Academic Search Index
Journal :
Measurement (02632241)
Publication Type :
Academic Journal
Accession number :
150850021
Full Text :
https://doi.org/10.1016/j.measurement.2021.109538