Modeling of Oil Viscosity for Southern Iraqi Reservoirs using Neural Network Method

Abstract

The calculation of the oil density is more complex due to a wide range of pressures
and temperatures, which are always determined by specific conditions, pressure and
temperature. Therefore, the calculations that depend on oil components are more
accurate and easier in finding such kind of requirements. The analyses of twenty live
oil samples are utilized. The three parameters Peng Robinson equation of state is
tuned to get match between measured and calculated oil viscosity. The Lohrenz-Bray-
Clark (LBC) viscosity calculation technique is adopted to calculate the viscosity of oil
from the given composition, pressure and temperature for 20 samples. The tuned
equation of state is used to generate oil viscosity values for a range of temperature and
pressure extends from the reservoir to surface conditions.
The generated viscosity data is utilized in the neural network tool (NN) to get fitting
model correlates the viscosity of oil with composition, pressure and temperature. The
resulted error and the correlation coefficient of the model constructed are close to 0
and 1 respectively. The NN model is also tested with data that are not used in set up
the model. The results proved the validity of the model. Moreover, the model’s
outcomes demonstrate its superiority to selected empirical correlations.