Application of several non-linear prediction tools for estimating uniaxial compressive strength of granitic rocks and comparison of their performances

Danial Jahed Armaghani, Edy Tonnizam Mohamad, Mohsen Hajihassani, Saffet Yagiz, Hossein Motaghedi

Research output: Contribution to journalArticle

38 Citations (Scopus)

Abstract

Uniaxial compressive strength (UCS) of rock is crucial for any type of projects constructed in/on rock mass. The test that is conducted to measure the UCS of rock is expensive, time consuming and having sample restriction. For this reason, the UCS of rock may be estimated using simple rock tests such as point load index (Is(50)), Schmidt hammer (Rn) and p-wave velocity (Vp) tests. To estimate the UCS of granitic rock as a function of relevant rock properties like Rn, p-wave and Is(50), the rock cores were collected from the face of the Pahang–Selangor fresh water tunnel in Malaysia. Afterwards, 124 samples are prepared and tested in accordance with relevant standards and the dataset is obtained. Further an established dataset is used for estimating the UCS of rock via three-nonlinear prediction tools, namely non-linear multiple regression (NLMR), artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). After conducting the mentioned models, considering several performance indices including coefficient of determination (R2), variance account for and root mean squared error and also using simple ranking procedure, the models were examined and the best prediction model was selected. It is concluded that the R2 equal to 0.951 for testing dataset suggests the superiority of the ANFIS model, while these values are 0.651 and 0.886 for NLMR and ANN techniques, respectively. The results pointed out that the ANFIS model can be used for predicting UCS of rocks with higher capacity in comparison with others. However, the developed model may be useful at a preliminary stage of design; it should be used with caution and only for the specified rock types.

Original languageEnglish
Pages (from-to)189-206
Number of pages18
JournalEngineering with Computers
Volume32
Issue number2
DOIs
Publication statusPublished - Apr 1 2016
Externally publishedYes

Fingerprint

Nonlinear Prediction
Compressive Strength
Compressive strength
Rocks
Adaptive Neuro-fuzzy Inference System
Nonlinear Regression
Multiple Regression
Fuzzy inference
Artificial Neural Network
Coefficient of Determination
Model
Malaysia
Performance Index
Tunnel
Mean Squared Error
Prediction Model
Ranking
Neural networks
Roots
Face

Keywords

  • Adaptive neuro-fuzzy inference system
  • Artificial neural network
  • Granite
  • Non-linear multiple regression
  • Uniaxial compressive strength

ASJC Scopus subject areas

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

Cite this

Application of several non-linear prediction tools for estimating uniaxial compressive strength of granitic rocks and comparison of their performances. / Jahed Armaghani, Danial; Tonnizam Mohamad, Edy; Hajihassani, Mohsen; Yagiz, Saffet; Motaghedi, Hossein.

In: Engineering with Computers, Vol. 32, No. 2, 01.04.2016, p. 189-206.

Research output: Contribution to journalArticle

Jahed Armaghani, Danial ; Tonnizam Mohamad, Edy ; Hajihassani, Mohsen ; Yagiz, Saffet ; Motaghedi, Hossein. / Application of several non-linear prediction tools for estimating uniaxial compressive strength of granitic rocks and comparison of their performances. In: Engineering with Computers. 2016 ; Vol. 32, No. 2. pp. 189-206.
@article{ed0a9ba659d84b9a9233b3540be2479e,
title = "Application of several non-linear prediction tools for estimating uniaxial compressive strength of granitic rocks and comparison of their performances",
abstract = "Uniaxial compressive strength (UCS) of rock is crucial for any type of projects constructed in/on rock mass. The test that is conducted to measure the UCS of rock is expensive, time consuming and having sample restriction. For this reason, the UCS of rock may be estimated using simple rock tests such as point load index (Is(50)), Schmidt hammer (Rn) and p-wave velocity (Vp) tests. To estimate the UCS of granitic rock as a function of relevant rock properties like Rn, p-wave and Is(50), the rock cores were collected from the face of the Pahang–Selangor fresh water tunnel in Malaysia. Afterwards, 124 samples are prepared and tested in accordance with relevant standards and the dataset is obtained. Further an established dataset is used for estimating the UCS of rock via three-nonlinear prediction tools, namely non-linear multiple regression (NLMR), artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). After conducting the mentioned models, considering several performance indices including coefficient of determination (R2), variance account for and root mean squared error and also using simple ranking procedure, the models were examined and the best prediction model was selected. It is concluded that the R2 equal to 0.951 for testing dataset suggests the superiority of the ANFIS model, while these values are 0.651 and 0.886 for NLMR and ANN techniques, respectively. The results pointed out that the ANFIS model can be used for predicting UCS of rocks with higher capacity in comparison with others. However, the developed model may be useful at a preliminary stage of design; it should be used with caution and only for the specified rock types.",
keywords = "Adaptive neuro-fuzzy inference system, Artificial neural network, Granite, Non-linear multiple regression, Uniaxial compressive strength",
author = "{Jahed Armaghani}, Danial and {Tonnizam Mohamad}, Edy and Mohsen Hajihassani and Saffet Yagiz and Hossein Motaghedi",
year = "2016",
month = "4",
day = "1",
doi = "10.1007/s00366-015-0410-5",
language = "English",
volume = "32",
pages = "189--206",
journal = "Engineering with Computers",
issn = "0177-0667",
publisher = "Springer London",
number = "2",

}

TY - JOUR

T1 - Application of several non-linear prediction tools for estimating uniaxial compressive strength of granitic rocks and comparison of their performances

AU - Jahed Armaghani, Danial

AU - Tonnizam Mohamad, Edy

AU - Hajihassani, Mohsen

AU - Yagiz, Saffet

AU - Motaghedi, Hossein

PY - 2016/4/1

Y1 - 2016/4/1

N2 - Uniaxial compressive strength (UCS) of rock is crucial for any type of projects constructed in/on rock mass. The test that is conducted to measure the UCS of rock is expensive, time consuming and having sample restriction. For this reason, the UCS of rock may be estimated using simple rock tests such as point load index (Is(50)), Schmidt hammer (Rn) and p-wave velocity (Vp) tests. To estimate the UCS of granitic rock as a function of relevant rock properties like Rn, p-wave and Is(50), the rock cores were collected from the face of the Pahang–Selangor fresh water tunnel in Malaysia. Afterwards, 124 samples are prepared and tested in accordance with relevant standards and the dataset is obtained. Further an established dataset is used for estimating the UCS of rock via three-nonlinear prediction tools, namely non-linear multiple regression (NLMR), artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). After conducting the mentioned models, considering several performance indices including coefficient of determination (R2), variance account for and root mean squared error and also using simple ranking procedure, the models were examined and the best prediction model was selected. It is concluded that the R2 equal to 0.951 for testing dataset suggests the superiority of the ANFIS model, while these values are 0.651 and 0.886 for NLMR and ANN techniques, respectively. The results pointed out that the ANFIS model can be used for predicting UCS of rocks with higher capacity in comparison with others. However, the developed model may be useful at a preliminary stage of design; it should be used with caution and only for the specified rock types.

AB - Uniaxial compressive strength (UCS) of rock is crucial for any type of projects constructed in/on rock mass. The test that is conducted to measure the UCS of rock is expensive, time consuming and having sample restriction. For this reason, the UCS of rock may be estimated using simple rock tests such as point load index (Is(50)), Schmidt hammer (Rn) and p-wave velocity (Vp) tests. To estimate the UCS of granitic rock as a function of relevant rock properties like Rn, p-wave and Is(50), the rock cores were collected from the face of the Pahang–Selangor fresh water tunnel in Malaysia. Afterwards, 124 samples are prepared and tested in accordance with relevant standards and the dataset is obtained. Further an established dataset is used for estimating the UCS of rock via three-nonlinear prediction tools, namely non-linear multiple regression (NLMR), artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). After conducting the mentioned models, considering several performance indices including coefficient of determination (R2), variance account for and root mean squared error and also using simple ranking procedure, the models were examined and the best prediction model was selected. It is concluded that the R2 equal to 0.951 for testing dataset suggests the superiority of the ANFIS model, while these values are 0.651 and 0.886 for NLMR and ANN techniques, respectively. The results pointed out that the ANFIS model can be used for predicting UCS of rocks with higher capacity in comparison with others. However, the developed model may be useful at a preliminary stage of design; it should be used with caution and only for the specified rock types.

KW - Adaptive neuro-fuzzy inference system

KW - Artificial neural network

KW - Granite

KW - Non-linear multiple regression

KW - Uniaxial compressive strength

UR - http://www.scopus.com/inward/record.url?scp=84961061738&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961061738&partnerID=8YFLogxK

U2 - 10.1007/s00366-015-0410-5

DO - 10.1007/s00366-015-0410-5

M3 - Article

VL - 32

SP - 189

EP - 206

JO - Engineering with Computers

JF - Engineering with Computers

SN - 0177-0667

IS - 2

ER -