Predicting the crude oil viscosity is very crucial to the oil industry. Accurate prediction of the viscosity will lead to a better design of an energy efficient transportation system and helps in determining the enhanced oil recovery method. There has been intensive work in generating viscosity empirical correlations for under–saturated, saturated and deal oil. Due to the rapid growth in computational capabilities, artificial neural networks (ANNs) are found to be a useful tool for the development of crude oil viscosity correlations. In this work, artificial neural networks (ANNs) model is developed to predict the viscosity of dead, saturated and under–saturated Omani crude oil. Detailed comparison was also made with 38 oil viscosity correlations using Omani crude oil viscosity database. Twelve of these correlations are for dead oil viscosity, 14 are for saturated oil viscosity and 12 for under–saturated oil viscosity. The oil viscosity data were collected from PVT reports. Statistical analysis and cross–plots showed that the ANN model outperformed the considered viscosity correlations.
Keywords: dead oil, saturated oil, under–saturated oil, viscosity correlations, Oman, crude oil viscosity, artificial neural networks, ANNs, light crude, oil and gas industry, petroleum engineering