Regression analysis and ANN models to predict rock properties from sound levels produced during drilling

B. Rajesh Kumar, Harsha Vardhan, M. Govindaraj, G. S. Vijay

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

This study aims to predict rock properties using soft computing techniques such as multiple regression, artificial neural network (MLP and RBF) models, taking drill bit speed, penetration rate, drill bit diameter and equivalent sound level produced during drilling as the input parameters. A database of 448 cases were tested for determination of uniaxial compressive strength (UCS), Schmidt rebound number (SRN), dry density (ρ), P-wave velocity (Vp), tensile strength (TS), modulus of elasticity (E) and percentage porosity (n) and the prediction capabilities of the models were then analyzed. Results from the analysis demonstrate that neural network approach is efficient when compared to statistical analysis in predicting rock properties from the sound level produced during drilling.

Original languageEnglish
Pages (from-to)61-72
Number of pages12
JournalInternational Journal of Rock Mechanics and Mining Sciences
Volume58
DOIs
Publication statusPublished - 01-02-2013

Fingerprint

drill bit
rock property
Regression analysis
Drilling
regression analysis
Rocks
drilling
Acoustic waves
Neural networks
Soft computing
dry density
tensile strength
compressive strength
artificial neural network
Compressive strength
elasticity
multiple regression
P-wave
wave velocity
Statistical methods

All Science Journal Classification (ASJC) codes

  • Geotechnical Engineering and Engineering Geology

Cite this

@article{d7d94f6309524d9a8c8b33487c4b7954,
title = "Regression analysis and ANN models to predict rock properties from sound levels produced during drilling",
abstract = "This study aims to predict rock properties using soft computing techniques such as multiple regression, artificial neural network (MLP and RBF) models, taking drill bit speed, penetration rate, drill bit diameter and equivalent sound level produced during drilling as the input parameters. A database of 448 cases were tested for determination of uniaxial compressive strength (UCS), Schmidt rebound number (SRN), dry density (ρ), P-wave velocity (Vp), tensile strength (TS), modulus of elasticity (E) and percentage porosity (n) and the prediction capabilities of the models were then analyzed. Results from the analysis demonstrate that neural network approach is efficient when compared to statistical analysis in predicting rock properties from the sound level produced during drilling.",
author = "{Rajesh Kumar}, B. and Harsha Vardhan and M. Govindaraj and Vijay, {G. S.}",
year = "2013",
month = "2",
day = "1",
doi = "10.1016/j.ijrmms.2012.10.002",
language = "English",
volume = "58",
pages = "61--72",
journal = "International Journal of Rock Mechanics and Minings Sciences",
issn = "1365-1609",
publisher = "Elsevier BV",

}

Regression analysis and ANN models to predict rock properties from sound levels produced during drilling. / Rajesh Kumar, B.; Vardhan, Harsha; Govindaraj, M.; Vijay, G. S.

In: International Journal of Rock Mechanics and Mining Sciences, Vol. 58, 01.02.2013, p. 61-72.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Regression analysis and ANN models to predict rock properties from sound levels produced during drilling

AU - Rajesh Kumar, B.

AU - Vardhan, Harsha

AU - Govindaraj, M.

AU - Vijay, G. S.

PY - 2013/2/1

Y1 - 2013/2/1

N2 - This study aims to predict rock properties using soft computing techniques such as multiple regression, artificial neural network (MLP and RBF) models, taking drill bit speed, penetration rate, drill bit diameter and equivalent sound level produced during drilling as the input parameters. A database of 448 cases were tested for determination of uniaxial compressive strength (UCS), Schmidt rebound number (SRN), dry density (ρ), P-wave velocity (Vp), tensile strength (TS), modulus of elasticity (E) and percentage porosity (n) and the prediction capabilities of the models were then analyzed. Results from the analysis demonstrate that neural network approach is efficient when compared to statistical analysis in predicting rock properties from the sound level produced during drilling.

AB - This study aims to predict rock properties using soft computing techniques such as multiple regression, artificial neural network (MLP and RBF) models, taking drill bit speed, penetration rate, drill bit diameter and equivalent sound level produced during drilling as the input parameters. A database of 448 cases were tested for determination of uniaxial compressive strength (UCS), Schmidt rebound number (SRN), dry density (ρ), P-wave velocity (Vp), tensile strength (TS), modulus of elasticity (E) and percentage porosity (n) and the prediction capabilities of the models were then analyzed. Results from the analysis demonstrate that neural network approach is efficient when compared to statistical analysis in predicting rock properties from the sound level produced during drilling.

UR - http://www.scopus.com/inward/record.url?scp=84869118573&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84869118573&partnerID=8YFLogxK

U2 - 10.1016/j.ijrmms.2012.10.002

DO - 10.1016/j.ijrmms.2012.10.002

M3 - Article

AN - SCOPUS:84869118573

VL - 58

SP - 61

EP - 72

JO - International Journal of Rock Mechanics and Minings Sciences

JF - International Journal of Rock Mechanics and Minings Sciences

SN - 1365-1609

ER -