Artificial neural networks and nonlinear regression techniques to assess the influence of slake durability cycles on the prediction of uniaxial compressive strength and modulus of elasticity for carbonate rocks

S. Yagiz, E. A. Sezer, C. Gokceoglu

Research output: Contribution to journalArticle

65 Citations (Scopus)

Abstract

Understanding rock material characterizations and solving relevant problems are quite difficult tasks because of their complex behavior, which sometimes cannot be identified without intelligent, numerical, and analytical approaches. Because of that, some prediction techniques, like artificial neural networks (ANN) and nonlinear regression techniques, can be utilized to solve those problems. The purpose of this study is to examine the effects of the cycling integer of slake durability index test on intact rock behavior and estimate some rock properties, such as uniaxial compressive strength (UCS) and modulus of elasticity (E) from known rock index parameters using ANN and various regression techniques. Further, new performance index (PI) and degree of consistency (Cd) are introduced to examine the accuracy of generated models. For these purposes, intact rock dataset is established by performing rock tests including uniaxial compressive strength, modulus of elasticity, Schmidt hammer, effective porosity, dry unit weight, p-wave velocity, and slake durability index tests on selected carbonate rocks. Afterward, the models are developed using ANN and nonlinear regression techniques. The concluding remark given is that four-cycle slake durability index (I d4) provides more accurate results to evaluate material characterization of carbonate rocks, and it is one of the reliable input variables to estimate UCS and E of carbonate rocks; introduced performance indices, both PI and Cd, may be accepted as good indicators to assess the accuracy of the complex models, and further, the ANN models have more prediction capability than the regression techniques to estimate relevant rock properties.

Original languageEnglish
Pages (from-to)1636-1650
Number of pages15
JournalInternational Journal for Numerical and Analytical Methods in Geomechanics
Volume36
Issue number14
DOIs
Publication statusPublished - Oct 10 2012
Externally publishedYes

Fingerprint

Carbonates
durability
compressive strength
carbonate rock
artificial neural network
Compressive strength
elasticity
Durability
Elastic moduli
Rocks
Neural networks
prediction
rock
rock property
uniaxial test
index
wave velocity
Hammers
porosity
Porosity

Keywords

  • Artificial neural networks
  • Modulus of elasticity
  • Nonlinear regression techniques
  • Performance indices, Slake durability cycles
  • Uniaxial compressive strength

ASJC Scopus subject areas

  • Computational Mechanics
  • Materials Science(all)
  • Geotechnical Engineering and Engineering Geology
  • Mechanics of Materials

Cite this

@article{eccc956404804bdfb5800bb1c1c818d9,
title = "Artificial neural networks and nonlinear regression techniques to assess the influence of slake durability cycles on the prediction of uniaxial compressive strength and modulus of elasticity for carbonate rocks",
abstract = "Understanding rock material characterizations and solving relevant problems are quite difficult tasks because of their complex behavior, which sometimes cannot be identified without intelligent, numerical, and analytical approaches. Because of that, some prediction techniques, like artificial neural networks (ANN) and nonlinear regression techniques, can be utilized to solve those problems. The purpose of this study is to examine the effects of the cycling integer of slake durability index test on intact rock behavior and estimate some rock properties, such as uniaxial compressive strength (UCS) and modulus of elasticity (E) from known rock index parameters using ANN and various regression techniques. Further, new performance index (PI) and degree of consistency (Cd) are introduced to examine the accuracy of generated models. For these purposes, intact rock dataset is established by performing rock tests including uniaxial compressive strength, modulus of elasticity, Schmidt hammer, effective porosity, dry unit weight, p-wave velocity, and slake durability index tests on selected carbonate rocks. Afterward, the models are developed using ANN and nonlinear regression techniques. The concluding remark given is that four-cycle slake durability index (I d4) provides more accurate results to evaluate material characterization of carbonate rocks, and it is one of the reliable input variables to estimate UCS and E of carbonate rocks; introduced performance indices, both PI and Cd, may be accepted as good indicators to assess the accuracy of the complex models, and further, the ANN models have more prediction capability than the regression techniques to estimate relevant rock properties.",
keywords = "Artificial neural networks, Modulus of elasticity, Nonlinear regression techniques, Performance indices, Slake durability cycles, Uniaxial compressive strength",
author = "S. Yagiz and Sezer, {E. A.} and C. Gokceoglu",
year = "2012",
month = "10",
day = "10",
doi = "10.1002/nag.1066",
language = "English",
volume = "36",
pages = "1636--1650",
journal = "International Journal for Numerical and Analytical Methods in Geomechanics",
issn = "0363-9061",
publisher = "John Wiley and Sons Ltd",
number = "14",

}

TY - JOUR

T1 - Artificial neural networks and nonlinear regression techniques to assess the influence of slake durability cycles on the prediction of uniaxial compressive strength and modulus of elasticity for carbonate rocks

AU - Yagiz, S.

AU - Sezer, E. A.

AU - Gokceoglu, C.

PY - 2012/10/10

Y1 - 2012/10/10

N2 - Understanding rock material characterizations and solving relevant problems are quite difficult tasks because of their complex behavior, which sometimes cannot be identified without intelligent, numerical, and analytical approaches. Because of that, some prediction techniques, like artificial neural networks (ANN) and nonlinear regression techniques, can be utilized to solve those problems. The purpose of this study is to examine the effects of the cycling integer of slake durability index test on intact rock behavior and estimate some rock properties, such as uniaxial compressive strength (UCS) and modulus of elasticity (E) from known rock index parameters using ANN and various regression techniques. Further, new performance index (PI) and degree of consistency (Cd) are introduced to examine the accuracy of generated models. For these purposes, intact rock dataset is established by performing rock tests including uniaxial compressive strength, modulus of elasticity, Schmidt hammer, effective porosity, dry unit weight, p-wave velocity, and slake durability index tests on selected carbonate rocks. Afterward, the models are developed using ANN and nonlinear regression techniques. The concluding remark given is that four-cycle slake durability index (I d4) provides more accurate results to evaluate material characterization of carbonate rocks, and it is one of the reliable input variables to estimate UCS and E of carbonate rocks; introduced performance indices, both PI and Cd, may be accepted as good indicators to assess the accuracy of the complex models, and further, the ANN models have more prediction capability than the regression techniques to estimate relevant rock properties.

AB - Understanding rock material characterizations and solving relevant problems are quite difficult tasks because of their complex behavior, which sometimes cannot be identified without intelligent, numerical, and analytical approaches. Because of that, some prediction techniques, like artificial neural networks (ANN) and nonlinear regression techniques, can be utilized to solve those problems. The purpose of this study is to examine the effects of the cycling integer of slake durability index test on intact rock behavior and estimate some rock properties, such as uniaxial compressive strength (UCS) and modulus of elasticity (E) from known rock index parameters using ANN and various regression techniques. Further, new performance index (PI) and degree of consistency (Cd) are introduced to examine the accuracy of generated models. For these purposes, intact rock dataset is established by performing rock tests including uniaxial compressive strength, modulus of elasticity, Schmidt hammer, effective porosity, dry unit weight, p-wave velocity, and slake durability index tests on selected carbonate rocks. Afterward, the models are developed using ANN and nonlinear regression techniques. The concluding remark given is that four-cycle slake durability index (I d4) provides more accurate results to evaluate material characterization of carbonate rocks, and it is one of the reliable input variables to estimate UCS and E of carbonate rocks; introduced performance indices, both PI and Cd, may be accepted as good indicators to assess the accuracy of the complex models, and further, the ANN models have more prediction capability than the regression techniques to estimate relevant rock properties.

KW - Artificial neural networks

KW - Modulus of elasticity

KW - Nonlinear regression techniques

KW - Performance indices, Slake durability cycles

KW - Uniaxial compressive strength

UR - http://www.scopus.com/inward/record.url?scp=84863921079&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863921079&partnerID=8YFLogxK

U2 - 10.1002/nag.1066

DO - 10.1002/nag.1066

M3 - Article

VL - 36

SP - 1636

EP - 1650

JO - International Journal for Numerical and Analytical Methods in Geomechanics

JF - International Journal for Numerical and Analytical Methods in Geomechanics

SN - 0363-9061

IS - 14

ER -