Viscosity and gas/oil ratio curves estimation using advances to neural networks

Amar Khoukhi; Munirudine Oloso; Elshafei Mostafa; Abdulazees Abdulraheem

doi:10.1109/WOSSPA.2011.5931460

Viscosity and gas/oil ratio curves estimation using advances to neural networks

Amar Khoukhi^*, Munirudine Oloso, Elshafei Mostafa, Abdulazees Abdulraheem

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

In oil and gas industry, prior prediction of certain properties is needed ahead of exploration and facility design. Viscosity and gas/oil ratio (GOR), are among those properties described through curves with their values varying over a specific range of reservoir pressures. However, the usual prediction approach could result into curves that are not consistent, exhibiting scattered behaviour as compared to the real curves. In this paper two advances to artificial neural networks are implemented to solve the problem. These are Support Vector Regressors and Functional Networks. Statistical error measures have been used and showed the high performance of the proposed techniques. Moreover, the predicted curves are consistent with the actual curves.

Original language	English
Title of host publication	7th International Workshop on Systems, Signal Processing and their Applications, WoSSPA 2011
Pages	235-238
Number of pages	4
DOIs	https://doi.org/10.1109/WOSSPA.2011.5931460
State	Published - 2011

Publication series

Name	7th International Workshop on Systems, Signal Processing and their Applications, WoSSPA 2011

Keywords

Functional Networks
Reservoir Characterization
Support Vector Regressors
Viscosity Gas/Oil Ratio

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/WOSSPA.2011.5931460

Cite this

Khoukhi, A., Oloso, M., Mostafa, E., & Abdulraheem, A. (2011). Viscosity and gas/oil ratio curves estimation using advances to neural networks. In 7th International Workshop on Systems, Signal Processing and their Applications, WoSSPA 2011 (pp. 235-238). Article 5931460 (7th International Workshop on Systems, Signal Processing and their Applications, WoSSPA 2011). https://doi.org/10.1109/WOSSPA.2011.5931460

@inproceedings{d01662f4dc904899914917c6d797fdd3,

title = "Viscosity and gas/oil ratio curves estimation using advances to neural networks",

abstract = "In oil and gas industry, prior prediction of certain properties is needed ahead of exploration and facility design. Viscosity and gas/oil ratio (GOR), are among those properties described through curves with their values varying over a specific range of reservoir pressures. However, the usual prediction approach could result into curves that are not consistent, exhibiting scattered behaviour as compared to the real curves. In this paper two advances to artificial neural networks are implemented to solve the problem. These are Support Vector Regressors and Functional Networks. Statistical error measures have been used and showed the high performance of the proposed techniques. Moreover, the predicted curves are consistent with the actual curves.",

keywords = "Functional Networks, Reservoir Characterization, Support Vector Regressors, Viscosity Gas/Oil Ratio",

author = "Amar Khoukhi and Munirudine Oloso and Elshafei Mostafa and Abdulazees Abdulraheem",

year = "2011",

doi = "10.1109/WOSSPA.2011.5931460",

language = "English",

isbn = "9781457706905",

series = "7th International Workshop on Systems, Signal Processing and their Applications, WoSSPA 2011",

pages = "235--238",

booktitle = "7th International Workshop on Systems, Signal Processing and their Applications, WoSSPA 2011",

}

Khoukhi, A, Oloso, M, Mostafa, E & Abdulraheem, A 2011, Viscosity and gas/oil ratio curves estimation using advances to neural networks. in 7th International Workshop on Systems, Signal Processing and their Applications, WoSSPA 2011., 5931460, 7th International Workshop on Systems, Signal Processing and their Applications, WoSSPA 2011, pp. 235-238. https://doi.org/10.1109/WOSSPA.2011.5931460

Viscosity and gas/oil ratio curves estimation using advances to neural networks. / Khoukhi, Amar; Oloso, Munirudine; Mostafa, Elshafei et al.
7th International Workshop on Systems, Signal Processing and their Applications, WoSSPA 2011. 2011. p. 235-238 5931460 (7th International Workshop on Systems, Signal Processing and their Applications, WoSSPA 2011).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Viscosity and gas/oil ratio curves estimation using advances to neural networks

AU - Khoukhi, Amar

AU - Oloso, Munirudine

AU - Mostafa, Elshafei

AU - Abdulraheem, Abdulazees

PY - 2011

Y1 - 2011

N2 - In oil and gas industry, prior prediction of certain properties is needed ahead of exploration and facility design. Viscosity and gas/oil ratio (GOR), are among those properties described through curves with their values varying over a specific range of reservoir pressures. However, the usual prediction approach could result into curves that are not consistent, exhibiting scattered behaviour as compared to the real curves. In this paper two advances to artificial neural networks are implemented to solve the problem. These are Support Vector Regressors and Functional Networks. Statistical error measures have been used and showed the high performance of the proposed techniques. Moreover, the predicted curves are consistent with the actual curves.

AB - In oil and gas industry, prior prediction of certain properties is needed ahead of exploration and facility design. Viscosity and gas/oil ratio (GOR), are among those properties described through curves with their values varying over a specific range of reservoir pressures. However, the usual prediction approach could result into curves that are not consistent, exhibiting scattered behaviour as compared to the real curves. In this paper two advances to artificial neural networks are implemented to solve the problem. These are Support Vector Regressors and Functional Networks. Statistical error measures have been used and showed the high performance of the proposed techniques. Moreover, the predicted curves are consistent with the actual curves.

KW - Functional Networks

KW - Reservoir Characterization

KW - Support Vector Regressors

KW - Viscosity Gas/Oil Ratio

UR - http://www.scopus.com/inward/record.url?scp=79960920308&partnerID=8YFLogxK

U2 - 10.1109/WOSSPA.2011.5931460

DO - 10.1109/WOSSPA.2011.5931460

M3 - Conference contribution

AN - SCOPUS:79960920308

SN - 9781457706905

T3 - 7th International Workshop on Systems, Signal Processing and their Applications, WoSSPA 2011

SP - 235

EP - 238

BT - 7th International Workshop on Systems, Signal Processing and their Applications, WoSSPA 2011

ER -

Khoukhi A, Oloso M, Mostafa E, Abdulraheem A. Viscosity and gas/oil ratio curves estimation using advances to neural networks. In 7th International Workshop on Systems, Signal Processing and their Applications, WoSSPA 2011. 2011. p. 235-238. 5931460. (7th International Workshop on Systems, Signal Processing and their Applications, WoSSPA 2011). doi: 10.1109/WOSSPA.2011.5931460

Viscosity and gas/oil ratio curves estimation using advances to neural networks

Abstract

Publication series

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Fingerprint

Cite this