Viscosity correlations for light Omani crude using artificial neural networks
by Talal Khamis Al-Wahaibi; Farouq S. Mjalli; Abdul-Aziz Al-Hashmi
International Journal of Petroleum Engineering (IJPE), Vol. 1, No. 1, 2014

Abstract: 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.

Online publication date: Sat, 26-Jul-2014

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Petroleum Engineering (IJPE):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com