Using Chemical Composition of Crude Oil and Artificial Intelligence Techniques to Predict the Reservoir Fluid Properties

Abstract

This study presents Artificial Neural Network (ANN) and Fuzzy Logic (FL) techniques to predict of some important reservoir fluid properties, like, bubble point pressure (Pb), oil formation volume factor at bubble point pressure (βo at Pb), and solution gas oil ratio at bubble point pressure (Rs at Pb) using chemical composition of crude oil. The presented models here were established using 1500 data points, collected from mainly unpublished sources. Statistical analysis was conducted to see which of the Artificial Intelligence techniques (AI) were more reliable and accurate for predicting the reservoir fluid properties. The new (FL) models outperformed most of the (ANN) models. The presented models provide good estimation for (Pb), βo at Pb, and Rs at Pb with correlation coefficient (R2) of 0.995, 0.991, and 0.998, respectively.