TY - JOUR
T1 - An intelligent approach to optimize multiphase subsea oil fields lifted by electrical submersible pumps
AU - Mohammadzaheri, Morteza
AU - Tafreshi, Reza
AU - Khan, Zurwa
AU - Franchek, Matthew
AU - Grigoriadis, Karolos
N1 - Funding Information:
This work was supported by NPRP grant from the Qatar National Research Fund (a member of Qatar Foundation), grant number is 08-398-2-160 .
Publisher Copyright:
© 2015 Elsevier B.V.
Copyright:
Copyright 2016 Elsevier B.V., All rights reserved.
PY - 2016/7/1
Y1 - 2016/7/1
N2 - This paper aims to introduce a method to maximize the profit of subsea petroleum fields lifted by electrical submersible pumps (ESPs). Unlike similar previous research which dealt with single-phase fluids, the reservoir is assumed to have oil, water and gas. Two major steps are taken in this research. First, algorithms including artificial neural networks (more specifically, multi-layer perceptrons) are developed to estimate head and brake horse power (BHP) of ESPs for gaseous fluids. These algorithms are essential to estimate the profit of the petroleum field. Second, an evolutionary algorithm is proposed and verified to maximize the profit. The proposed algorithm includes a newly devised stage that particularly facilitates solving heavily constrained problems. Finally, the methodology is employed to solve several sample problems.
AB - This paper aims to introduce a method to maximize the profit of subsea petroleum fields lifted by electrical submersible pumps (ESPs). Unlike similar previous research which dealt with single-phase fluids, the reservoir is assumed to have oil, water and gas. Two major steps are taken in this research. First, algorithms including artificial neural networks (more specifically, multi-layer perceptrons) are developed to estimate head and brake horse power (BHP) of ESPs for gaseous fluids. These algorithms are essential to estimate the profit of the petroleum field. Second, an evolutionary algorithm is proposed and verified to maximize the profit. The proposed algorithm includes a newly devised stage that particularly facilitates solving heavily constrained problems. Finally, the methodology is employed to solve several sample problems.
KW - Artificial neural networks
KW - Electrical submersible pump
KW - Evolutionary optimization
KW - Gaseous petroleum fluids
KW - Subsea oil field
UR - http://www.scopus.com/inward/record.url?scp=84949439455&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84949439455&partnerID=8YFLogxK
U2 - 10.1016/j.jocs.2015.10.009
DO - 10.1016/j.jocs.2015.10.009
M3 - Article
AN - SCOPUS:84949439455
SN - 1877-7503
VL - 15
SP - 50
EP - 59
JO - Journal of Computational Science
JF - Journal of Computational Science
ER -