Predict Reservoir Fluid Properties of Yemeni Crude Oils Using Fuzzy Logic Technique

Abstract

The aim of this paper is to predict the bubble point pressure (Pb), formation volume factor at bubble point pressure (βoat Pb), and solution gas oil ratio at bubble point pressure (Rs at Pb). The proposed models were based on field data including oil and gas specific gravity, and temperature. The data used in this study were collected from different wells in the different popular Yemeni reservoirs. An Artificial Intelligence (AI) proposed models were developed using Fuzzy Logic (FL) technique. The obtained results in this work showed high performance of the FL models. To validate the performance and accuracy of the proposed FL models, different evolution criteria were applied using various statistical error analysis such as an average absolute percent relative error (AAPRE), standard deviation (SD), and the correlation coefficient (R2). The results established the superiority of the FL models to predict the Pb, βo at Pb, and Rs at Pb high accuracy where the recorded correlation coefficients were 0.993, 0.995, and 0.990, respectively.