Pattern recognition insight into drilling optimization of shaly formations

Ali Chamkalani, Sohrab Zendehboudi, Mahmood Amani, Reza Chamkalani, Lesley James, Maurice Dusseault

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Slow drilling in deep shale formations leads to a considerable expenditure to the petroleum industry. An important factor that contributes to slow penetration rate is bit balling in water-reactive shale formations. Bit balling is recognized as the major reason for inefficient performance of the bit while drilling shaly formations. The corresponding research centers and industry are always interested in finding practical solutions to mitigate bit balling associated with slow shale drilling. In this study, three well-performing and robust pattern recognition techniques including linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and neural network pattern recognition (NNPR) are presented for problem identification in drilling engineering. Each method constructs three structures considering important inputs: normalized rate of penetration, depth of cut, specific energy, and cation exchange capacity to diagnose effective bit cleaning in shale formations of the Southern Oil Field in Iran. The models correlate operational parameters to cation exchange capacity to determine whether effective bit cleaning (reversal of balling) or ineffective cleaning (irreversible balling) is taking place. The common evaluation approaches include cross penalty error, confusion matrix output, area under the curve (AUC), and receiver operating characteristic (ROC) to evaluate efficiency of the multi-strategy classifier. These indicators provide useful information on the number of classified and misclassified cases, global accuracy, and discriminatory ability of diagnostic tests. We show that pattern recognition methods can assure both stability and high accuracy in classification situations.

Original languageEnglish
Pages (from-to)322-339
Number of pages18
JournalJournal of Petroleum Science and Engineering
Volume156
DOIs
Publication statusPublished - 1 Jan 2017

Fingerprint

pattern recognition
Pattern recognition
Drilling
shale
drilling
Shale
discriminant analysis
cation exchange capacity
Cleaning
penetration
Discriminant analysis
Ion exchange
Positive ions
oil field
expenditure
Petroleum industry
Oil fields
engineering
matrix
industry

Keywords

  • Cation exchange capacity
  • Confusion matrix
  • Cross entropy error
  • Effective drilling
  • Pattern recognition
  • Receiver operating characteristic
  • Shale

ASJC Scopus subject areas

  • Fuel Technology
  • Geotechnical Engineering and Engineering Geology

Cite this

Pattern recognition insight into drilling optimization of shaly formations. / Chamkalani, Ali; Zendehboudi, Sohrab; Amani, Mahmood; Chamkalani, Reza; James, Lesley; Dusseault, Maurice.

In: Journal of Petroleum Science and Engineering, Vol. 156, 01.01.2017, p. 322-339.

Research output: Contribution to journalArticle

Chamkalani, Ali ; Zendehboudi, Sohrab ; Amani, Mahmood ; Chamkalani, Reza ; James, Lesley ; Dusseault, Maurice. / Pattern recognition insight into drilling optimization of shaly formations. In: Journal of Petroleum Science and Engineering. 2017 ; Vol. 156. pp. 322-339.
@article{ef114c42bb6c4b0b821249bd3690cebc,
title = "Pattern recognition insight into drilling optimization of shaly formations",
abstract = "Slow drilling in deep shale formations leads to a considerable expenditure to the petroleum industry. An important factor that contributes to slow penetration rate is bit balling in water-reactive shale formations. Bit balling is recognized as the major reason for inefficient performance of the bit while drilling shaly formations. The corresponding research centers and industry are always interested in finding practical solutions to mitigate bit balling associated with slow shale drilling. In this study, three well-performing and robust pattern recognition techniques including linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and neural network pattern recognition (NNPR) are presented for problem identification in drilling engineering. Each method constructs three structures considering important inputs: normalized rate of penetration, depth of cut, specific energy, and cation exchange capacity to diagnose effective bit cleaning in shale formations of the Southern Oil Field in Iran. The models correlate operational parameters to cation exchange capacity to determine whether effective bit cleaning (reversal of balling) or ineffective cleaning (irreversible balling) is taking place. The common evaluation approaches include cross penalty error, confusion matrix output, area under the curve (AUC), and receiver operating characteristic (ROC) to evaluate efficiency of the multi-strategy classifier. These indicators provide useful information on the number of classified and misclassified cases, global accuracy, and discriminatory ability of diagnostic tests. We show that pattern recognition methods can assure both stability and high accuracy in classification situations.",
keywords = "Cation exchange capacity, Confusion matrix, Cross entropy error, Effective drilling, Pattern recognition, Receiver operating characteristic, Shale",
author = "Ali Chamkalani and Sohrab Zendehboudi and Mahmood Amani and Reza Chamkalani and Lesley James and Maurice Dusseault",
year = "2017",
month = "1",
day = "1",
doi = "10.1016/j.petrol.2017.05.017",
language = "English",
volume = "156",
pages = "322--339",
journal = "Journal of Petroleum Science and Engineering",
issn = "0920-4105",
publisher = "Elsevier",

}

TY - JOUR

T1 - Pattern recognition insight into drilling optimization of shaly formations

AU - Chamkalani, Ali

AU - Zendehboudi, Sohrab

AU - Amani, Mahmood

AU - Chamkalani, Reza

AU - James, Lesley

AU - Dusseault, Maurice

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Slow drilling in deep shale formations leads to a considerable expenditure to the petroleum industry. An important factor that contributes to slow penetration rate is bit balling in water-reactive shale formations. Bit balling is recognized as the major reason for inefficient performance of the bit while drilling shaly formations. The corresponding research centers and industry are always interested in finding practical solutions to mitigate bit balling associated with slow shale drilling. In this study, three well-performing and robust pattern recognition techniques including linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and neural network pattern recognition (NNPR) are presented for problem identification in drilling engineering. Each method constructs three structures considering important inputs: normalized rate of penetration, depth of cut, specific energy, and cation exchange capacity to diagnose effective bit cleaning in shale formations of the Southern Oil Field in Iran. The models correlate operational parameters to cation exchange capacity to determine whether effective bit cleaning (reversal of balling) or ineffective cleaning (irreversible balling) is taking place. The common evaluation approaches include cross penalty error, confusion matrix output, area under the curve (AUC), and receiver operating characteristic (ROC) to evaluate efficiency of the multi-strategy classifier. These indicators provide useful information on the number of classified and misclassified cases, global accuracy, and discriminatory ability of diagnostic tests. We show that pattern recognition methods can assure both stability and high accuracy in classification situations.

AB - Slow drilling in deep shale formations leads to a considerable expenditure to the petroleum industry. An important factor that contributes to slow penetration rate is bit balling in water-reactive shale formations. Bit balling is recognized as the major reason for inefficient performance of the bit while drilling shaly formations. The corresponding research centers and industry are always interested in finding practical solutions to mitigate bit balling associated with slow shale drilling. In this study, three well-performing and robust pattern recognition techniques including linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and neural network pattern recognition (NNPR) are presented for problem identification in drilling engineering. Each method constructs three structures considering important inputs: normalized rate of penetration, depth of cut, specific energy, and cation exchange capacity to diagnose effective bit cleaning in shale formations of the Southern Oil Field in Iran. The models correlate operational parameters to cation exchange capacity to determine whether effective bit cleaning (reversal of balling) or ineffective cleaning (irreversible balling) is taking place. The common evaluation approaches include cross penalty error, confusion matrix output, area under the curve (AUC), and receiver operating characteristic (ROC) to evaluate efficiency of the multi-strategy classifier. These indicators provide useful information on the number of classified and misclassified cases, global accuracy, and discriminatory ability of diagnostic tests. We show that pattern recognition methods can assure both stability and high accuracy in classification situations.

KW - Cation exchange capacity

KW - Confusion matrix

KW - Cross entropy error

KW - Effective drilling

KW - Pattern recognition

KW - Receiver operating characteristic

KW - Shale

UR - http://www.scopus.com/inward/record.url?scp=85020406901&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020406901&partnerID=8YFLogxK

U2 - 10.1016/j.petrol.2017.05.017

DO - 10.1016/j.petrol.2017.05.017

M3 - Article

AN - SCOPUS:85020406901

VL - 156

SP - 322

EP - 339

JO - Journal of Petroleum Science and Engineering

JF - Journal of Petroleum Science and Engineering

SN - 0920-4105

ER -