Predicting tunnel convergence in weak rocks: Multivariate adaptive regression spline and rough set theory approaches

A. C. Adoko, Y. Y. Jiao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

Knowing accurately the characteristics of the tunnel convergence is an essential task in tunneling, especially when the New Austrian Tunneling Method is applied; this allows making any necessary adjustment to the construction methods in order to avoid unwanted situations such as rock collapse, trapping and jamming of boring machine or geological disasters. This study aims at improving a Multivariate Adaptive Regression Spline (MARS) based model that has been proposed previously to predict the tunnel convergence in weak rocks. To this end, Rough Set (RS) theory was implemented to reduce the parameter attributes. The ground conditions were analyzed and the redundant input parameters which can be eliminated were identified objectively by determining the reduct sets. Field data were compiled from tunnel construction projects in Hunan province (China), which were used as case study. The input parameters included the class index of the surrounding rock mass, angle of internal friction, cohesion, Young's modulus, rock density, tunnel overburden, distance between the monitoring station and the tunnel heading face and the elapsed monitoring time. The performance of the models was evaluated by comparing the measured data to the predicted convergence values using several performance indices, namely the variance account for (VAF), root mean square error (RMSE), relative root mean square error mean absolute percentage error (RRMSE) and the coefficient of determination (R2). The results showed that all the input parameters as were identified as core (intersection of all reducts) except the Young's modulus and rock density which were consequently removed from the model. The computed performance indices before and after attribute reduction, were: 94.26 and 97.02; 0.42 and 0.28; 0.18 and 0.11; 0.95 and 0.98 for VAF, RMSE, RRMSE, and R2 respectively, indicating noticeable improvement. It is concluded that MARS along with RS can constitute a reliable alternative to existing approaches in dealing with nonlinear geo-engineering problem such as the tunnel convergence.

Original languageEnglish
Title of host publicationISRM International Symposium - 8th Asian Rock Mechanics Symposium, ARMS 2014
PublisherInternational Society for Rock Mechanics
Pages1218-1226
Number of pages9
ISBN (Electronic)9784907430030
Publication statusPublished - 2014
Event8th Asian Rock Mechanics Symposium, ARMS 2014 - Sapporo, Japan
Duration: Oct 14 2014Oct 16 2014

Other

Other8th Asian Rock Mechanics Symposium, ARMS 2014
CountryJapan
CitySapporo
Period10/14/1410/16/14

Fingerprint

weak rock
Rough set theory
splines
Splines
set theory
tunnels
regression analysis
Tunnels
tunnel
Rocks
rocks
root-mean-square errors
Mean square error
Young modulus
rock
boring machines
modulus of elasticity
Elastic moduli
NATM
jamming

All Science Journal Classification (ASJC) codes

  • Geophysics
  • Geochemistry and Petrology

Cite this

Adoko, A. C., & Jiao, Y. Y. (2014). Predicting tunnel convergence in weak rocks: Multivariate adaptive regression spline and rough set theory approaches. In ISRM International Symposium - 8th Asian Rock Mechanics Symposium, ARMS 2014 (pp. 1218-1226). International Society for Rock Mechanics.
Adoko, A. C. ; Jiao, Y. Y. / Predicting tunnel convergence in weak rocks : Multivariate adaptive regression spline and rough set theory approaches. ISRM International Symposium - 8th Asian Rock Mechanics Symposium, ARMS 2014. International Society for Rock Mechanics, 2014. pp. 1218-1226
@inproceedings{efab00d5e3434e38b4afa96dec760bce,
title = "Predicting tunnel convergence in weak rocks: Multivariate adaptive regression spline and rough set theory approaches",
abstract = "Knowing accurately the characteristics of the tunnel convergence is an essential task in tunneling, especially when the New Austrian Tunneling Method is applied; this allows making any necessary adjustment to the construction methods in order to avoid unwanted situations such as rock collapse, trapping and jamming of boring machine or geological disasters. This study aims at improving a Multivariate Adaptive Regression Spline (MARS) based model that has been proposed previously to predict the tunnel convergence in weak rocks. To this end, Rough Set (RS) theory was implemented to reduce the parameter attributes. The ground conditions were analyzed and the redundant input parameters which can be eliminated were identified objectively by determining the reduct sets. Field data were compiled from tunnel construction projects in Hunan province (China), which were used as case study. The input parameters included the class index of the surrounding rock mass, angle of internal friction, cohesion, Young's modulus, rock density, tunnel overburden, distance between the monitoring station and the tunnel heading face and the elapsed monitoring time. The performance of the models was evaluated by comparing the measured data to the predicted convergence values using several performance indices, namely the variance account for (VAF), root mean square error (RMSE), relative root mean square error mean absolute percentage error (RRMSE) and the coefficient of determination (R2). The results showed that all the input parameters as were identified as core (intersection of all reducts) except the Young's modulus and rock density which were consequently removed from the model. The computed performance indices before and after attribute reduction, were: 94.26 and 97.02; 0.42 and 0.28; 0.18 and 0.11; 0.95 and 0.98 for VAF, RMSE, RRMSE, and R2 respectively, indicating noticeable improvement. It is concluded that MARS along with RS can constitute a reliable alternative to existing approaches in dealing with nonlinear geo-engineering problem such as the tunnel convergence.",
author = "Adoko, {A. C.} and Jiao, {Y. Y.}",
year = "2014",
language = "English",
pages = "1218--1226",
booktitle = "ISRM International Symposium - 8th Asian Rock Mechanics Symposium, ARMS 2014",
publisher = "International Society for Rock Mechanics",

}

Adoko, AC & Jiao, YY 2014, Predicting tunnel convergence in weak rocks: Multivariate adaptive regression spline and rough set theory approaches. in ISRM International Symposium - 8th Asian Rock Mechanics Symposium, ARMS 2014. International Society for Rock Mechanics, pp. 1218-1226, 8th Asian Rock Mechanics Symposium, ARMS 2014, Sapporo, Japan, 10/14/14.

Predicting tunnel convergence in weak rocks : Multivariate adaptive regression spline and rough set theory approaches. / Adoko, A. C.; Jiao, Y. Y.

ISRM International Symposium - 8th Asian Rock Mechanics Symposium, ARMS 2014. International Society for Rock Mechanics, 2014. p. 1218-1226.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Predicting tunnel convergence in weak rocks

T2 - Multivariate adaptive regression spline and rough set theory approaches

AU - Adoko, A. C.

AU - Jiao, Y. Y.

PY - 2014

Y1 - 2014

N2 - Knowing accurately the characteristics of the tunnel convergence is an essential task in tunneling, especially when the New Austrian Tunneling Method is applied; this allows making any necessary adjustment to the construction methods in order to avoid unwanted situations such as rock collapse, trapping and jamming of boring machine or geological disasters. This study aims at improving a Multivariate Adaptive Regression Spline (MARS) based model that has been proposed previously to predict the tunnel convergence in weak rocks. To this end, Rough Set (RS) theory was implemented to reduce the parameter attributes. The ground conditions were analyzed and the redundant input parameters which can be eliminated were identified objectively by determining the reduct sets. Field data were compiled from tunnel construction projects in Hunan province (China), which were used as case study. The input parameters included the class index of the surrounding rock mass, angle of internal friction, cohesion, Young's modulus, rock density, tunnel overburden, distance between the monitoring station and the tunnel heading face and the elapsed monitoring time. The performance of the models was evaluated by comparing the measured data to the predicted convergence values using several performance indices, namely the variance account for (VAF), root mean square error (RMSE), relative root mean square error mean absolute percentage error (RRMSE) and the coefficient of determination (R2). The results showed that all the input parameters as were identified as core (intersection of all reducts) except the Young's modulus and rock density which were consequently removed from the model. The computed performance indices before and after attribute reduction, were: 94.26 and 97.02; 0.42 and 0.28; 0.18 and 0.11; 0.95 and 0.98 for VAF, RMSE, RRMSE, and R2 respectively, indicating noticeable improvement. It is concluded that MARS along with RS can constitute a reliable alternative to existing approaches in dealing with nonlinear geo-engineering problem such as the tunnel convergence.

AB - Knowing accurately the characteristics of the tunnel convergence is an essential task in tunneling, especially when the New Austrian Tunneling Method is applied; this allows making any necessary adjustment to the construction methods in order to avoid unwanted situations such as rock collapse, trapping and jamming of boring machine or geological disasters. This study aims at improving a Multivariate Adaptive Regression Spline (MARS) based model that has been proposed previously to predict the tunnel convergence in weak rocks. To this end, Rough Set (RS) theory was implemented to reduce the parameter attributes. The ground conditions were analyzed and the redundant input parameters which can be eliminated were identified objectively by determining the reduct sets. Field data were compiled from tunnel construction projects in Hunan province (China), which were used as case study. The input parameters included the class index of the surrounding rock mass, angle of internal friction, cohesion, Young's modulus, rock density, tunnel overburden, distance between the monitoring station and the tunnel heading face and the elapsed monitoring time. The performance of the models was evaluated by comparing the measured data to the predicted convergence values using several performance indices, namely the variance account for (VAF), root mean square error (RMSE), relative root mean square error mean absolute percentage error (RRMSE) and the coefficient of determination (R2). The results showed that all the input parameters as were identified as core (intersection of all reducts) except the Young's modulus and rock density which were consequently removed from the model. The computed performance indices before and after attribute reduction, were: 94.26 and 97.02; 0.42 and 0.28; 0.18 and 0.11; 0.95 and 0.98 for VAF, RMSE, RRMSE, and R2 respectively, indicating noticeable improvement. It is concluded that MARS along with RS can constitute a reliable alternative to existing approaches in dealing with nonlinear geo-engineering problem such as the tunnel convergence.

UR - http://www.scopus.com/inward/record.url?scp=84962463232&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962463232&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84962463232

SP - 1218

EP - 1226

BT - ISRM International Symposium - 8th Asian Rock Mechanics Symposium, ARMS 2014

PB - International Society for Rock Mechanics

ER -

Adoko AC, Jiao YY. Predicting tunnel convergence in weak rocks: Multivariate adaptive regression spline and rough set theory approaches. In ISRM International Symposium - 8th Asian Rock Mechanics Symposium, ARMS 2014. International Society for Rock Mechanics. 2014. p. 1218-1226