TY - JOUR AU - Heidarian, Mohamad AU - Karimnezhad, Masoud AU - Schaffie, Mahin AU - Ranjbar, Mohammad PY - 2017/07/26 Y2 - 2024/03/28 TI - A new empirical correlation for estimating bubble point pressure using the genetic algorithm JF - Geology, Geophysics and Environment JA - geol VL - 43 IS - 1 SE - Articles DO - 10.7494/geol.2017.43.1.33 UR - https://journals.agh.edu.pl/geol/article/view/2050 SP - 33 AB - <p>In this paper, a new and more accurate correlation to predict bubble point pressure (Pb) for Middle East crudes by using the genetic algorithm (GA) is attempted. For this purpose, a total of 286 data sets of different crude oils from Middle East reservoirs were used as training data for constructing the correlation. The general form of the correlation was found by several regressive examinations. To improve the correlation, the genetic algorithm was applied. To validate the correlation, 143 data sets of different crudes from Middle East reservoirs which were different from the training data were used as test data for calculating mean absolute relative error (MARE) and correlation coefficient (R2) between the predicted values from the proposed correlation and the experimental values. In addition, the MARE and R2 were calculated for previous correlation in the test data. The results show that the proposed correlation is more accurate than all of the previous correlations exclusively for Middle East crudes.</p> ER -