A support vector regression model for predicting tunnel boring machine penetration rates

Satar Mahdevari, Kourosh Shahriar, Saffet Yagiz, Mohsen Akbarpour Shirazi

Research output: Contribution to journalArticle

41 Citations (Scopus)

Abstract

With widespread increasing applications of mechanized tunneling in almost all ground conditions, prediction of tunnel boring machine (TBM) performance is required for time planning, cost control and choice of excavation method in order to make tunneling economical. Penetration rate is a principal measure of full-face TBM performance and is used to evaluate the feasibility of the machine and predict advance rate of excavation. This research aims at developing a regression model to predict penetration rate of TBM in hard rock conditions based on a new artificial intelligence (AI) algorithm namely support vector regression (SVR). For this purpose, the Queens Water Tunnel, in New York City, was selected as a case study to test the proposed model. In order to find out the optimum values of the parameters and prevent over-fitting, 80% of the total data were selected randomly for training set and the rest were kept for testing the model. According to the results, it can be said that the proposed model is a useful and reliable means to predict TBM penetration rate provided that a suitable dataset exists. From the prediction results of training and testing samples, the squared correlation coefficient (R2) between the observed and predicted values of the proposed model was obtained 0.99 and 0.95, respectively, which shows a high conformity between predicted and actual penetration rate.

Original languageEnglish
Pages (from-to)214-229
Number of pages16
JournalInternational Journal of Rock Mechanics and Mining Sciences
Volume72
DOIs
Publication statusPublished - Dec 1 2014
Externally publishedYes

Fingerprint

TBM
Tunnels
penetration
Excavation
excavation
advance rate
artificial intelligence
ground conditions
Testing
hard rock
prediction
Artificial intelligence
tunnel
Rocks
rate
Planning
cost
Costs
Water
water

Keywords

  • Penetration rate
  • Queens water tunnel
  • SVR
  • TBM performance

ASJC Scopus subject areas

  • Geotechnical Engineering and Engineering Geology

Cite this

A support vector regression model for predicting tunnel boring machine penetration rates. / Mahdevari, Satar; Shahriar, Kourosh; Yagiz, Saffet; Akbarpour Shirazi, Mohsen.

In: International Journal of Rock Mechanics and Mining Sciences, Vol. 72, 01.12.2014, p. 214-229.

Research output: Contribution to journalArticle

@article{1799a9c8426647e2b7223c1b6443a6cb,
title = "A support vector regression model for predicting tunnel boring machine penetration rates",
abstract = "With widespread increasing applications of mechanized tunneling in almost all ground conditions, prediction of tunnel boring machine (TBM) performance is required for time planning, cost control and choice of excavation method in order to make tunneling economical. Penetration rate is a principal measure of full-face TBM performance and is used to evaluate the feasibility of the machine and predict advance rate of excavation. This research aims at developing a regression model to predict penetration rate of TBM in hard rock conditions based on a new artificial intelligence (AI) algorithm namely support vector regression (SVR). For this purpose, the Queens Water Tunnel, in New York City, was selected as a case study to test the proposed model. In order to find out the optimum values of the parameters and prevent over-fitting, 80{\%} of the total data were selected randomly for training set and the rest were kept for testing the model. According to the results, it can be said that the proposed model is a useful and reliable means to predict TBM penetration rate provided that a suitable dataset exists. From the prediction results of training and testing samples, the squared correlation coefficient (R2) between the observed and predicted values of the proposed model was obtained 0.99 and 0.95, respectively, which shows a high conformity between predicted and actual penetration rate.",
keywords = "Penetration rate, Queens water tunnel, SVR, TBM performance",
author = "Satar Mahdevari and Kourosh Shahriar and Saffet Yagiz and {Akbarpour Shirazi}, Mohsen",
year = "2014",
month = "12",
day = "1",
doi = "10.1016/j.ijrmms.2014.09.012",
language = "English",
volume = "72",
pages = "214--229",
journal = "International Journal of Rock Mechanics and Minings Sciences",
issn = "1365-1609",
publisher = "Elsevier",

}

TY - JOUR

T1 - A support vector regression model for predicting tunnel boring machine penetration rates

AU - Mahdevari, Satar

AU - Shahriar, Kourosh

AU - Yagiz, Saffet

AU - Akbarpour Shirazi, Mohsen

PY - 2014/12/1

Y1 - 2014/12/1

N2 - With widespread increasing applications of mechanized tunneling in almost all ground conditions, prediction of tunnel boring machine (TBM) performance is required for time planning, cost control and choice of excavation method in order to make tunneling economical. Penetration rate is a principal measure of full-face TBM performance and is used to evaluate the feasibility of the machine and predict advance rate of excavation. This research aims at developing a regression model to predict penetration rate of TBM in hard rock conditions based on a new artificial intelligence (AI) algorithm namely support vector regression (SVR). For this purpose, the Queens Water Tunnel, in New York City, was selected as a case study to test the proposed model. In order to find out the optimum values of the parameters and prevent over-fitting, 80% of the total data were selected randomly for training set and the rest were kept for testing the model. According to the results, it can be said that the proposed model is a useful and reliable means to predict TBM penetration rate provided that a suitable dataset exists. From the prediction results of training and testing samples, the squared correlation coefficient (R2) between the observed and predicted values of the proposed model was obtained 0.99 and 0.95, respectively, which shows a high conformity between predicted and actual penetration rate.

AB - With widespread increasing applications of mechanized tunneling in almost all ground conditions, prediction of tunnel boring machine (TBM) performance is required for time planning, cost control and choice of excavation method in order to make tunneling economical. Penetration rate is a principal measure of full-face TBM performance and is used to evaluate the feasibility of the machine and predict advance rate of excavation. This research aims at developing a regression model to predict penetration rate of TBM in hard rock conditions based on a new artificial intelligence (AI) algorithm namely support vector regression (SVR). For this purpose, the Queens Water Tunnel, in New York City, was selected as a case study to test the proposed model. In order to find out the optimum values of the parameters and prevent over-fitting, 80% of the total data were selected randomly for training set and the rest were kept for testing the model. According to the results, it can be said that the proposed model is a useful and reliable means to predict TBM penetration rate provided that a suitable dataset exists. From the prediction results of training and testing samples, the squared correlation coefficient (R2) between the observed and predicted values of the proposed model was obtained 0.99 and 0.95, respectively, which shows a high conformity between predicted and actual penetration rate.

KW - Penetration rate

KW - Queens water tunnel

KW - SVR

KW - TBM performance

UR - http://www.scopus.com/inward/record.url?scp=84949115475&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949115475&partnerID=8YFLogxK

U2 - 10.1016/j.ijrmms.2014.09.012

DO - 10.1016/j.ijrmms.2014.09.012

M3 - Article

VL - 72

SP - 214

EP - 229

JO - International Journal of Rock Mechanics and Minings Sciences

JF - International Journal of Rock Mechanics and Minings Sciences

SN - 1365-1609

ER -