An intelligent approach to optimize multiphase subsea oil fields lifted by electrical submersible pumps

Morteza Mohammadzaheri, Reza Tafreshi, Zurwa Khan, Matthew Franchek, Karolos Grigoriadis

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)50-59
Number of pages10
JournalJournal of Computational Science
Volume15
DOIs
Publication statusPublished - Jul 1 2016

    Fingerprint

Keywords

  • Artificial neural networks
  • Electrical submersible pump
  • Evolutionary optimization
  • Gaseous petroleum fluids
  • Subsea oil field

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)
  • Modelling and Simulation

Cite this