Prediction of the uniaxial compressive strength of sandstone using various modeling techniques

Danial Jahed Armaghani, Mohd For Mohd Amin, Saffet Yagiz, Roohollah Shirani Faradonbeh, Rini Asnida Abdullah

Research output: Contribution to journalArticle

39 Citations (Scopus)

Abstract

Sandstone blocks were collected from Dengkil site in Malaysia and brought to laboratory, and then intact samples prepared for testing. Rock tests, including Schmidt hammer rebound number, P-wave velocity, point load index, and UCS were conducted. The established dataset is composed of 108 cases. Consequently, the established dataset was utilized for developing the simple regression, linear, non-linear multiple regressions, artificial neural network, and a hybrid model, developed by integrating imperialist competitive algorithm with ANN. After performing the relevant models, several performance indices i.e. root mean squared error, coefficient of determination, variance account for, and total ranking, are examined for selecting the best model and comparing the obtained results. It is obtained that the ICA-ANN model is superior to the others. It is concluded that the hybrid of ICA-ANN could be used for predicting UCS of similar rock type in practice.

Original languageEnglish
Pages (from-to)174-186
Number of pages13
JournalInternational Journal of Rock Mechanics and Mining Sciences
Volume85
DOIs
Publication statusPublished - May 1 2016
Externally publishedYes

Fingerprint

Sandstone
compressive strength
Compressive strength
sandstone
Independent component analysis
prediction
modeling
Rocks
Hammers
Linear regression
rock
artificial neural network
multiple regression
ranking
P-wave
wave velocity
Neural networks
Testing
index

Keywords

  • Artificial neural network
  • Imperialist competitive algorithm
  • Non-destructive tests
  • Point load index
  • Uniaxial compressive strength

ASJC Scopus subject areas

  • Geotechnical Engineering and Engineering Geology

Cite this

Prediction of the uniaxial compressive strength of sandstone using various modeling techniques. / Jahed Armaghani, Danial; Mohd Amin, Mohd For; Yagiz, Saffet; Faradonbeh, Roohollah Shirani; Abdullah, Rini Asnida.

In: International Journal of Rock Mechanics and Mining Sciences, Vol. 85, 01.05.2016, p. 174-186.

Research output: Contribution to journalArticle

Jahed Armaghani, Danial ; Mohd Amin, Mohd For ; Yagiz, Saffet ; Faradonbeh, Roohollah Shirani ; Abdullah, Rini Asnida. / Prediction of the uniaxial compressive strength of sandstone using various modeling techniques. In: International Journal of Rock Mechanics and Mining Sciences. 2016 ; Vol. 85. pp. 174-186.
@article{8c4cde610c654821bde4908e1408769b,
title = "Prediction of the uniaxial compressive strength of sandstone using various modeling techniques",
abstract = "Sandstone blocks were collected from Dengkil site in Malaysia and brought to laboratory, and then intact samples prepared for testing. Rock tests, including Schmidt hammer rebound number, P-wave velocity, point load index, and UCS were conducted. The established dataset is composed of 108 cases. Consequently, the established dataset was utilized for developing the simple regression, linear, non-linear multiple regressions, artificial neural network, and a hybrid model, developed by integrating imperialist competitive algorithm with ANN. After performing the relevant models, several performance indices i.e. root mean squared error, coefficient of determination, variance account for, and total ranking, are examined for selecting the best model and comparing the obtained results. It is obtained that the ICA-ANN model is superior to the others. It is concluded that the hybrid of ICA-ANN could be used for predicting UCS of similar rock type in practice.",
keywords = "Artificial neural network, Imperialist competitive algorithm, Non-destructive tests, Point load index, Uniaxial compressive strength",
author = "{Jahed Armaghani}, Danial and {Mohd Amin}, {Mohd For} and Saffet Yagiz and Faradonbeh, {Roohollah Shirani} and Abdullah, {Rini Asnida}",
year = "2016",
month = "5",
day = "1",
doi = "10.1016/j.ijrmms.2016.03.018",
language = "English",
volume = "85",
pages = "174--186",
journal = "International Journal of Rock Mechanics and Minings Sciences",
issn = "1365-1609",
publisher = "Elsevier",

}

TY - JOUR

T1 - Prediction of the uniaxial compressive strength of sandstone using various modeling techniques

AU - Jahed Armaghani, Danial

AU - Mohd Amin, Mohd For

AU - Yagiz, Saffet

AU - Faradonbeh, Roohollah Shirani

AU - Abdullah, Rini Asnida

PY - 2016/5/1

Y1 - 2016/5/1

N2 - Sandstone blocks were collected from Dengkil site in Malaysia and brought to laboratory, and then intact samples prepared for testing. Rock tests, including Schmidt hammer rebound number, P-wave velocity, point load index, and UCS were conducted. The established dataset is composed of 108 cases. Consequently, the established dataset was utilized for developing the simple regression, linear, non-linear multiple regressions, artificial neural network, and a hybrid model, developed by integrating imperialist competitive algorithm with ANN. After performing the relevant models, several performance indices i.e. root mean squared error, coefficient of determination, variance account for, and total ranking, are examined for selecting the best model and comparing the obtained results. It is obtained that the ICA-ANN model is superior to the others. It is concluded that the hybrid of ICA-ANN could be used for predicting UCS of similar rock type in practice.

AB - Sandstone blocks were collected from Dengkil site in Malaysia and brought to laboratory, and then intact samples prepared for testing. Rock tests, including Schmidt hammer rebound number, P-wave velocity, point load index, and UCS were conducted. The established dataset is composed of 108 cases. Consequently, the established dataset was utilized for developing the simple regression, linear, non-linear multiple regressions, artificial neural network, and a hybrid model, developed by integrating imperialist competitive algorithm with ANN. After performing the relevant models, several performance indices i.e. root mean squared error, coefficient of determination, variance account for, and total ranking, are examined for selecting the best model and comparing the obtained results. It is obtained that the ICA-ANN model is superior to the others. It is concluded that the hybrid of ICA-ANN could be used for predicting UCS of similar rock type in practice.

KW - Artificial neural network

KW - Imperialist competitive algorithm

KW - Non-destructive tests

KW - Point load index

KW - Uniaxial compressive strength

UR - http://www.scopus.com/inward/record.url?scp=84962409054&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962409054&partnerID=8YFLogxK

U2 - 10.1016/j.ijrmms.2016.03.018

DO - 10.1016/j.ijrmms.2016.03.018

M3 - Article

VL - 85

SP - 174

EP - 186

JO - International Journal of Rock Mechanics and Minings Sciences

JF - International Journal of Rock Mechanics and Minings Sciences

SN - 1365-1609

ER -