PREDICTION OF TWO-PHASE PRESSURE DROP USING ARTIFICIAL NEURAL NETWORK

Document Type : Original Article

Authors

1 Mechanical Power Engineering Dept., Faculty of Engineering, Menoufia University, Shebin Elkom, Egypt.

2 Mechanical Power Engineering Dept., Faculty of Engineering, Menoufia University, Shebin Elkom, Egypt

3 MAGAPETCO - Magawish Petroleum Co., Cairo, Egypt

Abstract

In the present paper an Artificial Neural Network (ANN) model is proposed to predict the two-phase pressure
drop in oil and gas field. In this model, the effect of number of hidden layers and number of neurons in each
layer is selected to generate independent results. In addition, the selected database contains 7581 data sets
selected from four different sources from which 1165 data sets are collected from the flowing wells of
Magapetco at East Esh Mallaha Marine (EEMM) field. The comparison between ANN predictions and other
popular models reveals that the ANN model can predict the pressure drop with fair accuracy. Furthermore, the
proposed model is used to predict the pressure distribution along the wall of flowing wells as well as the bottom
hole flowing pressure and good accuracy was obtained.

Keywords

Files

Share

How to cite

Statistics