Experimental Investigation of the Effects of Fluid Viscosity on Electrical Submersible Pumps Performance

Abstract

Summary Electrical submersible pumps (ESPs) are an important artificial lift method used in oil production. ESPs can provide high production flow rate, are flexible, and can be installed in highly deviated wells, subsea deepwater wells, or on the seabed. ESP performance is generally characterized by manufacturers using only water as fluid. However, oil properties are very different from water and significantly alter the pump’s performance. Operating ESPs with viscous fluids leads to degraded pump performance. Therefore, knowing the ESP’s performance when pumping viscous fluid is essential to properly design the production system. In this work, we present an experimental study of ESP performance operating with viscous flow. A total of six ESP models were tested, operating at four different rotational speeds and 11 viscosities, resulting in a comprehensive database of more than 5,800 operating conditions. This database contributes to the literature given the lack of available data. We also perform a phenomenological analysis on the influence of operational parameters, such as viscosity, rotational speed, specific speed, and rotational Reynolds number. The database and analyses performed are central for future models predicting the viscous performance of ESPs. The results from our investigation and tests showed that the increase in viscosity causes (1) a reduction in the head and (2) an increase in drive power, resulting in (3) a sharp decrease in efficiency. However, increasing rotational speed tends to mitigate this performance degradation. Efficiency and flow rate correction factors are virtually independent of the flow rate within the recommended operating region. This is not true for the head correction factor, which is not constant. The pump geometry seems to influence its performance as ESPs with higher specific speed are less impaired by viscous effects. The database obtained in the present work is available in the data repository of the University of Campinas, at the address presented by Monte Verde et al. (2022).