Fuzzy Sequential Forward Search for Oil Formation Volume Factor Predictive Tool Factor for Niger Delta Crude Oil
K. K. Salam *
Petroleum Engineering Unit, Department of Chemical Engineering, P.M.B. 4000, Ladoke Akintola University of Technology (LAUTECH), Ogbomoso, Nigeria
D. O. Araromi
Petroleum Engineering Unit, Department of Chemical Engineering, P.M.B. 4000, Ladoke Akintola University of Technology (LAUTECH), Ogbomoso, Nigeria
A. O. Arinkoola
Petroleum Engineering Unit, Department of Chemical Engineering, P.M.B. 4000, Ladoke Akintola University of Technology (LAUTECH), Ogbomoso, Nigeria
S. S. Ikiensikimama
Departments of Petroleum & Gas Engineering, University of Port Harcourt, Port Harcourt, Nigeria
*Author to whom correspondence should be addressed.
Abstract
Accurate prediction of fluid properties is essentials for all reservoir engineering calculations such as estimation of reserves, well testing analysis and in numerical reservoir simulation. Oil formation volume factor is one of the properties that can either be gotten from empirical or experimental method.
This work focuses on the use of fuzzy sequential forward techniques to develop a oil formation volume factor model using 1,316 data obtained from 45 different oil fields in the Niger Delta, Nigeria. The data set was randomly divided into two parts with 750 used for training and 566 for testing. The model developed has the lowest Root Mean Square Error (RMSE) of 0.0784 when compared with published correlation used for prediction. The accuracy of the developed model was tested with cross plot and statistical analysis. The model developed outperformed the existing correlations when subjected to further statistical analysis.
Keywords: Formation volume factor, fuzzy inference system, correlation, artificial intelligence, root mean square error