Function development for appraising brittleness of intact rocks using genetic programming and non-linear multiple regression models

Manoj Khandelwal, Roohollah Shirani Faradonbeh, Masoud Monjezi, Danial Jahed Armaghani, Muhd Zaimi Bin Abd Majid, Saffet Yagiz

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Brittleness of rock is one of the most critical features for design of underground excavation project. Therefore, proper assessing of rock brittleness can be very useful for designers and evaluators of geotechnical applications. In this study, feasibility of genetic programming (GP) model and non-linear multiple regression (NLMR) in predicting brittleness of intact rocks is examined. For this purpose, a dataset developed by conducting various rock tests including uniaxial compressive strength, Brazilian tensile strength, unit weight and brittleness via punch penetration on rock samples gathered from 48 tunnels projects around the world is utilized herein. Considering multiple inputs, several GP models were constructed to estimate brittleness index of the rock and finally, the best GP model was selected. Note that, GP can make an equation for predicting output of the system using model inputs. To show applicability of the developed GP model, non-linear multiple regression (NLMR) was also applied and developed. Considering some model performance indices, performance prediction of the GP and NLMR models were evaluated and it was found that the GP model is superior to NLMR one. Based on coefficient of determination (R2) of testing datasets, by proposing GP model, it can be improved from 0.882 (obtained by NLMR model) to 0.904. It is worth mentioning that the proposed predictive models in this study should be planned and used for the similar types of rock and the established inputs ranges.

Original languageEnglish
Pages (from-to)13-21
Number of pages9
JournalEngineering with Computers
Volume33
Issue number1
DOIs
Publication statusPublished - Jan 1 2017
Externally publishedYes

Fingerprint

Genetic programming
Nonlinear Regression
Multiple Regression
Multiple Models
Brittleness
Genetic Programming
Regression Model
Rocks
Programming Model
Coefficient of Determination
Compressive Strength
Tensile Strength
Performance Prediction
Predictive Model
Performance Index
Tunnel
Penetration
Excavation
Compressive strength
Testing

Keywords

  • Brittleness
  • Genetic programming
  • Non-linear multiple regression

ASJC Scopus subject areas

  • Engineering(all)
  • Software
  • Modelling and Simulation
  • Computer Science Applications

Cite this

Function development for appraising brittleness of intact rocks using genetic programming and non-linear multiple regression models. / Khandelwal, Manoj; Shirani Faradonbeh, Roohollah; Monjezi, Masoud; Armaghani, Danial Jahed; Majid, Muhd Zaimi Bin Abd; Yagiz, Saffet.

In: Engineering with Computers, Vol. 33, No. 1, 01.01.2017, p. 13-21.

Research output: Contribution to journalArticle

Khandelwal, Manoj ; Shirani Faradonbeh, Roohollah ; Monjezi, Masoud ; Armaghani, Danial Jahed ; Majid, Muhd Zaimi Bin Abd ; Yagiz, Saffet. / Function development for appraising brittleness of intact rocks using genetic programming and non-linear multiple regression models. In: Engineering with Computers. 2017 ; Vol. 33, No. 1. pp. 13-21.
@article{69771cecd0534567afa7bed7421425a5,
title = "Function development for appraising brittleness of intact rocks using genetic programming and non-linear multiple regression models",
abstract = "Brittleness of rock is one of the most critical features for design of underground excavation project. Therefore, proper assessing of rock brittleness can be very useful for designers and evaluators of geotechnical applications. In this study, feasibility of genetic programming (GP) model and non-linear multiple regression (NLMR) in predicting brittleness of intact rocks is examined. For this purpose, a dataset developed by conducting various rock tests including uniaxial compressive strength, Brazilian tensile strength, unit weight and brittleness via punch penetration on rock samples gathered from 48 tunnels projects around the world is utilized herein. Considering multiple inputs, several GP models were constructed to estimate brittleness index of the rock and finally, the best GP model was selected. Note that, GP can make an equation for predicting output of the system using model inputs. To show applicability of the developed GP model, non-linear multiple regression (NLMR) was also applied and developed. Considering some model performance indices, performance prediction of the GP and NLMR models were evaluated and it was found that the GP model is superior to NLMR one. Based on coefficient of determination (R2) of testing datasets, by proposing GP model, it can be improved from 0.882 (obtained by NLMR model) to 0.904. It is worth mentioning that the proposed predictive models in this study should be planned and used for the similar types of rock and the established inputs ranges.",
keywords = "Brittleness, Genetic programming, Non-linear multiple regression",
author = "Manoj Khandelwal and {Shirani Faradonbeh}, Roohollah and Masoud Monjezi and Armaghani, {Danial Jahed} and Majid, {Muhd Zaimi Bin Abd} and Saffet Yagiz",
year = "2017",
month = "1",
day = "1",
doi = "10.1007/s00366-016-0452-3",
language = "English",
volume = "33",
pages = "13--21",
journal = "Engineering with Computers",
issn = "0177-0667",
publisher = "Springer London",
number = "1",

}

TY - JOUR

T1 - Function development for appraising brittleness of intact rocks using genetic programming and non-linear multiple regression models

AU - Khandelwal, Manoj

AU - Shirani Faradonbeh, Roohollah

AU - Monjezi, Masoud

AU - Armaghani, Danial Jahed

AU - Majid, Muhd Zaimi Bin Abd

AU - Yagiz, Saffet

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Brittleness of rock is one of the most critical features for design of underground excavation project. Therefore, proper assessing of rock brittleness can be very useful for designers and evaluators of geotechnical applications. In this study, feasibility of genetic programming (GP) model and non-linear multiple regression (NLMR) in predicting brittleness of intact rocks is examined. For this purpose, a dataset developed by conducting various rock tests including uniaxial compressive strength, Brazilian tensile strength, unit weight and brittleness via punch penetration on rock samples gathered from 48 tunnels projects around the world is utilized herein. Considering multiple inputs, several GP models were constructed to estimate brittleness index of the rock and finally, the best GP model was selected. Note that, GP can make an equation for predicting output of the system using model inputs. To show applicability of the developed GP model, non-linear multiple regression (NLMR) was also applied and developed. Considering some model performance indices, performance prediction of the GP and NLMR models were evaluated and it was found that the GP model is superior to NLMR one. Based on coefficient of determination (R2) of testing datasets, by proposing GP model, it can be improved from 0.882 (obtained by NLMR model) to 0.904. It is worth mentioning that the proposed predictive models in this study should be planned and used for the similar types of rock and the established inputs ranges.

AB - Brittleness of rock is one of the most critical features for design of underground excavation project. Therefore, proper assessing of rock brittleness can be very useful for designers and evaluators of geotechnical applications. In this study, feasibility of genetic programming (GP) model and non-linear multiple regression (NLMR) in predicting brittleness of intact rocks is examined. For this purpose, a dataset developed by conducting various rock tests including uniaxial compressive strength, Brazilian tensile strength, unit weight and brittleness via punch penetration on rock samples gathered from 48 tunnels projects around the world is utilized herein. Considering multiple inputs, several GP models were constructed to estimate brittleness index of the rock and finally, the best GP model was selected. Note that, GP can make an equation for predicting output of the system using model inputs. To show applicability of the developed GP model, non-linear multiple regression (NLMR) was also applied and developed. Considering some model performance indices, performance prediction of the GP and NLMR models were evaluated and it was found that the GP model is superior to NLMR one. Based on coefficient of determination (R2) of testing datasets, by proposing GP model, it can be improved from 0.882 (obtained by NLMR model) to 0.904. It is worth mentioning that the proposed predictive models in this study should be planned and used for the similar types of rock and the established inputs ranges.

KW - Brittleness

KW - Genetic programming

KW - Non-linear multiple regression

UR - http://www.scopus.com/inward/record.url?scp=84965010968&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84965010968&partnerID=8YFLogxK

U2 - 10.1007/s00366-016-0452-3

DO - 10.1007/s00366-016-0452-3

M3 - Article

VL - 33

SP - 13

EP - 21

JO - Engineering with Computers

JF - Engineering with Computers

SN - 0177-0667

IS - 1

ER -