Modelling of petroleum multiphase flow in electrical submersible pumps with shallow artificial neural networks

ABSTRACT

This paper first investigates existing empirical models which predict head or pressure increase of two-phase petroleum fluids in electrical submersible pumps (ESPs); then, proposes an alternative model, a shallow artificial neural network (ANN) for the same purpose. Empirical models of ESP are widely used; whereas, analytical models are still unappealing due to their reliance on over-simplified assumptions, need to excessive extent of information or lack of accuracy. The proposed shallow ANN is trained and cross-validated with the same data used in developing a number of empirical models; however, the ANN evidently outperforms those empirical models in terms of accuracy in the entire operating area. Mean of absolute prediction error of the ANN, for the experimental data not used in its training, is 69% less than the most accurate existing empirical model.

KEYWORDS:

• Electrical submersible pump
• empirical model
• shallow artificial neural network
• multiphase petroleum fluid

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes on contributors

Morteza Mohammadzaheri completed his Bachelor and Masters of Mechanical Engineering at K.N.Toosi University of Technology and University of Tehran, Iran. Then, he received his PhD in Intelligent Control from the School of Mechanical Engineering, University of Adelaide, Australia, in 2011. Dr Mohammadzaheri is currently an Assistant Professor of Dynamic Systems and Control, at Mechanical and Industrial Engineering Department of Sultan Qaboos University, Oman. His research includes modelling, control and optimisation of systems particularly with use of artificial intelligence.

Reza Tafreshi completed his Bachelor and Masters of Mechanical Engineering at K.N.Toosi University, Iran. Then, he received his PhD from University of British Columbia, Canada, in 2005. He currently serves as an Associate Professor of Mechanical Engineering at Qatar campus of Texam A&M University.

Zurwa Khan completed her Bachelor of Mechanical Engineering at Qatar campus of Texam A&M University in 2013 and serves as a researcher at the same institute.

Mojatba Ghodsi received his BSc and MSc degrees in Mechanical Engineering from Isfahan University of Technology (1999) and Tehran Polytechnic (2001), Iran. He then completed his PhD (2007) and JSPS postdoctoral fellowship (2009) at Precision Engineering Department, University of Tokyo, Japan. He is now an Assistant Professor at Mechanical and Industrial Engineering Department, Sultan Qaboos University, Oman.

Mathew Franchek received his Bachelor, Master and PhD in Mechanical Engineering from Texas A&M University in 1987, 1988 and 1991, respectively. He has served as the director of Subsea Engineering at University of Houston, USA, where he is currently a Professor of Mechanical Engineering.

Karolos Grigoriadis completed his Bachelor of Mechanical Engineering at National Technical University of Athens, Greece, 1987, followed by a Master of Aerospace Engineering program at Virginia Polytechnic Institute & State University, 1989. He then received a Master of Mathematics (1993) and a PhD in Aeronautics and Astronautics (1994) from Purdue University, USA. He is currently a Professor of Mechanical Engineering and the Director of Aerospace Engineering at University of Houston, USA.

ORCID

Morteza Mohammadzaheri http://orcid.org/0000-0002-8187-6375

Additional information

Funding

This work was supported by NPRP grant from the Qatar National Research Fund (a member of Qatar Foundation), grant number is 7-1114-2-415.