Academic Journals Database
Disseminating quality controlled scientific knowledge

PREDICTION OF NIGERIAN CRUDE OIL VISCOSITY USING ARTIFICIAL NEURAL NETWORK

ADD TO MY LIST
 
Author(s): O. Omole | O.A. Falode | Deng A. Deng

Journal: Petroleum and Coal
ISSN 1337-7027

Volume: 51;
Issue: 3;
Start page: 181;
Date: 2009;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Viscosity | Oil | Empirical | Neural Network | Back propagation.

ABSTRACT
The viscosity parameter is a very important fluid property in reservoir engineering computations. Itshould be determined in the laboratory but most of the time; the data is not either reliable orunavailable. Hence, empirical correlations were derived to estimate them. However, the success of thecorrelations in prediction depends on the range of data at which they were originally developed in the region.In this study, artificial neural network (ANN) was used to address the inaccuracy of empiricalcorrelations used for predicting crude oil viscosity. The new artificial neural network model wasdeveloped to predict the crude oil viscosity using 32 data sets collected from the Niger Delta Region ofNigeria. About 17 data sets were used to train the model, 10 sets were used to test the accuracy of themodel, and remaining 5sets to validate the relationships established during the training process. Thetest results revealed that the back propagation neural network model (BPNN) were better than theempirical correlations in terms of average absolute relative error and correlation coefficient.
Save time & money - Smart Internet Solutions      Why do you need a reservation system?