The Application of Artificial Neural Networks for the Prediction of Oil Production Flow Rate

Abstract

Estimation of oil production flow rate, where direct rate measurement is not feasible, is a challenge faced by petroleum engineers in some fields throughout the world. In such situations, oil flow rate is commonly estimated using empirical correlations. In some cases, significant error is inherent in application of the empirical correlations and yields inaccurate results. This study presents a new methodology for prediction of oil flow rate in two-phase flow of oil and gas through wellhead chokes using the artificial neural network technique. The developed model predicts oil flow rate as functions of choke upstream pressure, choke size, and producing gas to oil ratio. The accuracy of the developed model was compared with some popular empirical correlations. Results of comparison showed that oil flow rates predicted by the new model are in excellent agreement with actual measured data.