Modeling rock mass deformation modulus using adaptive techniques

A. C. Adoko, T. Zvarivadza

Research output: Contribution to conferencePaper

Abstract

The deformation modulus (Em) of rock mass is an important parameter used in designing underground excavations. It models the mechanical response of rock mass due to excavation and can be determined directly using large scale in-situ tests which are often time consuming and expensive. To overcome this issue, several empirical equations are usually employed. However, these existing equations are suitable for certain types of rock masses posing limitations. Therefore, this paper intends to investigate alternatives for estimating the Em using adaptive techniques namely, the Adaptive Neuro-fuzzy Inference systems (ANFIS) and Multivariate Adaptive Regression Spline (MARS). Available data on the Em was employed to establish the models. The input parameters used to develop the models included the uniaxial compression strength, rock quality designation, discontinuity characteristics and the rock mass rating index. The performances of proposed models were evaluated using various performance indices namely the variance account for (VAF), root-mean square error (RMSE), and the coefficient of determination (R2). The results indicated good accuracy. Overall, the MARS model showed lower performance compared with the ANFIS model but the MARS model was able to produce easy-to-interpret.

Original languageEnglish
Publication statusPublished - Jan 1 2018
Event52nd U.S. Rock Mechanics/Geomechanics Symposium - Seattle, United States
Duration: Jun 17 2018Jun 20 2018

Conference

Conference52nd U.S. Rock Mechanics/Geomechanics Symposium
CountryUnited States
CitySeattle
Period6/17/186/20/18

Fingerprint

Rocks
rocks
rock
splines
modeling
Splines
regression analysis
excavation
Fuzzy inference
inference
Excavation
rock quality designation
in situ test
root-mean-square errors
ratings
Mean square error
discontinuity
Compaction
estimating
compression

ASJC Scopus subject areas

  • Geophysics
  • Geochemistry and Petrology

Cite this

Adoko, A. C., & Zvarivadza, T. (2018). Modeling rock mass deformation modulus using adaptive techniques. Paper presented at 52nd U.S. Rock Mechanics/Geomechanics Symposium, Seattle, United States.

Modeling rock mass deformation modulus using adaptive techniques. / Adoko, A. C.; Zvarivadza, T.

2018. Paper presented at 52nd U.S. Rock Mechanics/Geomechanics Symposium, Seattle, United States.

Research output: Contribution to conferencePaper

Adoko, AC & Zvarivadza, T 2018, 'Modeling rock mass deformation modulus using adaptive techniques' Paper presented at 52nd U.S. Rock Mechanics/Geomechanics Symposium, Seattle, United States, 6/17/18 - 6/20/18, .
Adoko AC, Zvarivadza T. Modeling rock mass deformation modulus using adaptive techniques. 2018. Paper presented at 52nd U.S. Rock Mechanics/Geomechanics Symposium, Seattle, United States.
Adoko, A. C. ; Zvarivadza, T. / Modeling rock mass deformation modulus using adaptive techniques. Paper presented at 52nd U.S. Rock Mechanics/Geomechanics Symposium, Seattle, United States.
@conference{61061d973129440ba6e830e7bcadc179,
title = "Modeling rock mass deformation modulus using adaptive techniques",
abstract = "The deformation modulus (Em) of rock mass is an important parameter used in designing underground excavations. It models the mechanical response of rock mass due to excavation and can be determined directly using large scale in-situ tests which are often time consuming and expensive. To overcome this issue, several empirical equations are usually employed. However, these existing equations are suitable for certain types of rock masses posing limitations. Therefore, this paper intends to investigate alternatives for estimating the Em using adaptive techniques namely, the Adaptive Neuro-fuzzy Inference systems (ANFIS) and Multivariate Adaptive Regression Spline (MARS). Available data on the Em was employed to establish the models. The input parameters used to develop the models included the uniaxial compression strength, rock quality designation, discontinuity characteristics and the rock mass rating index. The performances of proposed models were evaluated using various performance indices namely the variance account for (VAF), root-mean square error (RMSE), and the coefficient of determination (R2). The results indicated good accuracy. Overall, the MARS model showed lower performance compared with the ANFIS model but the MARS model was able to produce easy-to-interpret.",
author = "Adoko, {A. C.} and T. Zvarivadza",
year = "2018",
month = "1",
day = "1",
language = "English",
note = "52nd U.S. Rock Mechanics/Geomechanics Symposium ; Conference date: 17-06-2018 Through 20-06-2018",

}

TY - CONF

T1 - Modeling rock mass deformation modulus using adaptive techniques

AU - Adoko, A. C.

AU - Zvarivadza, T.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The deformation modulus (Em) of rock mass is an important parameter used in designing underground excavations. It models the mechanical response of rock mass due to excavation and can be determined directly using large scale in-situ tests which are often time consuming and expensive. To overcome this issue, several empirical equations are usually employed. However, these existing equations are suitable for certain types of rock masses posing limitations. Therefore, this paper intends to investigate alternatives for estimating the Em using adaptive techniques namely, the Adaptive Neuro-fuzzy Inference systems (ANFIS) and Multivariate Adaptive Regression Spline (MARS). Available data on the Em was employed to establish the models. The input parameters used to develop the models included the uniaxial compression strength, rock quality designation, discontinuity characteristics and the rock mass rating index. The performances of proposed models were evaluated using various performance indices namely the variance account for (VAF), root-mean square error (RMSE), and the coefficient of determination (R2). The results indicated good accuracy. Overall, the MARS model showed lower performance compared with the ANFIS model but the MARS model was able to produce easy-to-interpret.

AB - The deformation modulus (Em) of rock mass is an important parameter used in designing underground excavations. It models the mechanical response of rock mass due to excavation and can be determined directly using large scale in-situ tests which are often time consuming and expensive. To overcome this issue, several empirical equations are usually employed. However, these existing equations are suitable for certain types of rock masses posing limitations. Therefore, this paper intends to investigate alternatives for estimating the Em using adaptive techniques namely, the Adaptive Neuro-fuzzy Inference systems (ANFIS) and Multivariate Adaptive Regression Spline (MARS). Available data on the Em was employed to establish the models. The input parameters used to develop the models included the uniaxial compression strength, rock quality designation, discontinuity characteristics and the rock mass rating index. The performances of proposed models were evaluated using various performance indices namely the variance account for (VAF), root-mean square error (RMSE), and the coefficient of determination (R2). The results indicated good accuracy. Overall, the MARS model showed lower performance compared with the ANFIS model but the MARS model was able to produce easy-to-interpret.

UR - http://www.scopus.com/inward/record.url?scp=85053456625&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053456625&partnerID=8YFLogxK

M3 - Paper

ER -