Application of artificial intelligence for technical screening of enhanced oil recovery methods

Geraldo A. R. Ramos, Lateef Akanji

Research output: Contribution to journalArticle

18 Downloads (Pure)

Abstract

An artificial intelligence technique based on five (5) layered feedforward backpropagation algorithm is applied in this study for technical screening of enhanced oil recovery (EOR) methods. Explicit knowledge pattern associated with the field data are extracted by taking advantage of the robustness of fuzzy logic reasoning and learning capability of neural networks. Associated field data
from successful EOR projects include parameters such as depth, porosity, permeability, viscosity, oil API and oil saturation. These parameters were used as input and predicted output in the training and validation processes, respectively. The developed model was then tested by using data set from Block T of the Angolan oilfield. Sensitivity analysis was performed between the Mandani
and the Takagi Sugero (TSK) model approach incorporated in the algorithm. The results of the sensitivity analysis have shown the robustness of the ANFIS approach in comparison to other approaches for the prediction of suitable EOR technique. Five nonregression models (linear, potential, logarithm, power and polynomial) were applied to evaluate the accuracy of the model between
the trained and the tested data set. The results of simulation show that hydrocarbon gas, polymer, combustion and CO2 are the suitable EOR techniques and could be used for further experimental and numerical studies.
Original languageEnglish
Article number00002
Pages (from-to)1-12
Number of pages12
JournalJournal of Oil, Gas and Petrochemical Sciences
Volume1
Issue number1
Publication statusPublished - 19 Dec 2017

Fingerprint

Artificial intelligence
Screening
Recovery
Sensitivity analysis
Backpropagation algorithms
Application programming interfaces (API)
Fuzzy logic
Oils
Porosity
Hydrocarbons
Polynomials
Viscosity
Neural networks
Polymers
Gases

Keywords

  • Enhanced Oil Recovery (EOR)
  • neuro-fuzzy
  • artificial intelligence
  • reservoir screening
  • neural network

Cite this

Application of artificial intelligence for technical screening of enhanced oil recovery methods. / Ramos, Geraldo A. R.; Akanji, Lateef.

In: Journal of Oil, Gas and Petrochemical Sciences, Vol. 1, No. 1, 00002, 19.12.2017, p. 1-12.

Research output: Contribution to journalArticle

@article{bd27c6f44bd64217bf6e01d6286804f2,
title = "Application of artificial intelligence for technical screening of enhanced oil recovery methods",
abstract = "An artificial intelligence technique based on five (5) layered feedforward backpropagation algorithm is applied in this study for technical screening of enhanced oil recovery (EOR) methods. Explicit knowledge pattern associated with the field data are extracted by taking advantage of the robustness of fuzzy logic reasoning and learning capability of neural networks. Associated field datafrom successful EOR projects include parameters such as depth, porosity, permeability, viscosity, oil API and oil saturation. These parameters were used as input and predicted output in the training and validation processes, respectively. The developed model was then tested by using data set from Block T of the Angolan oilfield. Sensitivity analysis was performed between the Mandaniand the Takagi Sugero (TSK) model approach incorporated in the algorithm. The results of the sensitivity analysis have shown the robustness of the ANFIS approach in comparison to other approaches for the prediction of suitable EOR technique. Five nonregression models (linear, potential, logarithm, power and polynomial) were applied to evaluate the accuracy of the model betweenthe trained and the tested data set. The results of simulation show that hydrocarbon gas, polymer, combustion and CO2 are the suitable EOR techniques and could be used for further experimental and numerical studies.",
keywords = "Enhanced Oil Recovery (EOR), neuro-fuzzy, artificial intelligence, reservoir screening, neural network",
author = "Ramos, {Geraldo A. R.} and Lateef Akanji",
note = "Acknowledgment This study is sponsored by the Angolan National Oil Company (Sonangol EP) and the authors are grateful for their support and the permission to use data and publish this manuscript.",
year = "2017",
month = "12",
day = "19",
language = "English",
volume = "1",
pages = "1--12",
journal = "Journal of Oil, Gas and Petrochemical Sciences",
number = "1",

}

TY - JOUR

T1 - Application of artificial intelligence for technical screening of enhanced oil recovery methods

AU - Ramos, Geraldo A. R.

AU - Akanji, Lateef

N1 - Acknowledgment This study is sponsored by the Angolan National Oil Company (Sonangol EP) and the authors are grateful for their support and the permission to use data and publish this manuscript.

PY - 2017/12/19

Y1 - 2017/12/19

N2 - An artificial intelligence technique based on five (5) layered feedforward backpropagation algorithm is applied in this study for technical screening of enhanced oil recovery (EOR) methods. Explicit knowledge pattern associated with the field data are extracted by taking advantage of the robustness of fuzzy logic reasoning and learning capability of neural networks. Associated field datafrom successful EOR projects include parameters such as depth, porosity, permeability, viscosity, oil API and oil saturation. These parameters were used as input and predicted output in the training and validation processes, respectively. The developed model was then tested by using data set from Block T of the Angolan oilfield. Sensitivity analysis was performed between the Mandaniand the Takagi Sugero (TSK) model approach incorporated in the algorithm. The results of the sensitivity analysis have shown the robustness of the ANFIS approach in comparison to other approaches for the prediction of suitable EOR technique. Five nonregression models (linear, potential, logarithm, power and polynomial) were applied to evaluate the accuracy of the model betweenthe trained and the tested data set. The results of simulation show that hydrocarbon gas, polymer, combustion and CO2 are the suitable EOR techniques and could be used for further experimental and numerical studies.

AB - An artificial intelligence technique based on five (5) layered feedforward backpropagation algorithm is applied in this study for technical screening of enhanced oil recovery (EOR) methods. Explicit knowledge pattern associated with the field data are extracted by taking advantage of the robustness of fuzzy logic reasoning and learning capability of neural networks. Associated field datafrom successful EOR projects include parameters such as depth, porosity, permeability, viscosity, oil API and oil saturation. These parameters were used as input and predicted output in the training and validation processes, respectively. The developed model was then tested by using data set from Block T of the Angolan oilfield. Sensitivity analysis was performed between the Mandaniand the Takagi Sugero (TSK) model approach incorporated in the algorithm. The results of the sensitivity analysis have shown the robustness of the ANFIS approach in comparison to other approaches for the prediction of suitable EOR technique. Five nonregression models (linear, potential, logarithm, power and polynomial) were applied to evaluate the accuracy of the model betweenthe trained and the tested data set. The results of simulation show that hydrocarbon gas, polymer, combustion and CO2 are the suitable EOR techniques and could be used for further experimental and numerical studies.

KW - Enhanced Oil Recovery (EOR)

KW - neuro-fuzzy

KW - artificial intelligence

KW - reservoir screening

KW - neural network

M3 - Article

VL - 1

SP - 1

EP - 12

JO - Journal of Oil, Gas and Petrochemical Sciences

JF - Journal of Oil, Gas and Petrochemical Sciences

IS - 1

M1 - 00002

ER -