Internal Friction Angle of Cohesionless Binary Mixture Sand-Granular Rubber Using Experimental Study and Machine Learning
Created by W.Langdon from
gp-bibliography.bib Revision:1.8081
- @Article{daghistani:2023:Geosciences,
-
author = "Firas Daghistani and Abolfazl Baghbani and
Hossam {Abuel Naga} and Roohollah Shirani Faradonbeh",
-
title = "Internal Friction Angle of Cohesionless Binary Mixture
{Sand-Granular} Rubber Using Experimental Study and
Machine Learning",
-
journal = "Geosciences",
-
year = "2023",
-
volume = "13",
-
number = "7",
-
pages = "Article No. 197",
-
keywords = "genetic algorithms, genetic programming",
-
ISSN = "2076-3263",
-
URL = "https://www.mdpi.com/2076-3263/13/7/197",
-
DOI = "doi:10.3390/geosciences13070197",
-
abstract = "This study aimed to examine the shear strength
characteristics of sand-granular rubber mixtures in
direct shear tests. Two different sizes of rubber and
one of sand were used in the experiment, with the sand
being mixed with various percentages of rubber
(0percent, 10percent, 20percent, 30percent, and
50percent). The mixtures were prepared at three
different densities (loose, slightly dense, and dense),
and shear stress was tested at four normal stresses
(30, 55, 105, and 200 kPa). The results of 80 direct
shear tests were used to calculate the peak and
residual internal friction angles of the mixtures, and
it was found that the normal stress had a significant
effect on the internal friction angle, with an increase
in normal stress leading to a decrease in the internal
friction angle. These results indicated that the
Mohr-Coulomb theory, which applies to rigid particles
only, is not applicable in sand-rubber mixtures, where
stiff particles (sand) and soft particles (rubber) are
mixed. The shear strength of the mixtures was also
influenced by multiple factors, including particle
morphology (size ratio, shape, and gradation), mixture
density, and normal stress. For the first time in the
literature, genetic programming, classification and
regression random forests, and multiple linear
regression were used to predict the peak and residual
internal friction angles. The genetic programming
resulted in the creation of two new equations based on
mixture unit weight, normal stress, and rubber content.
Both artificial intelligence models were found to be
capable of accurately predicting the peak and residual
internal friction angles of sand-rubber mixtures.",
-
notes = "also known as \cite{geosciences13070197}",
- }
Genetic Programming entries for
Firas Daghistani
Abolfazl Baghbani
Hossam Abuel-Naga
Roohollah Shirani Faradonbeh
Citations