New correlations for dew-point pressure for gas condensate

New Models with three different techniques have been developed to predict the dew-point pressure for gas condensate reservoirs. Traditional correlations, non-parametric approaches and artificial neural networks have been utilized in this study. The new models are function of easily obtained parameters (reservoir temperature, gas specific gravity, condensate specific gravity and gas-oil ratio). A total number of 113 data sets obtained from Constant Mass Expansion experiment (CME) were collected from Middle East fields; has been used in developing the models. The data used for developing the models covers a reservoir temperature from 100 to 309 oF, gas oil ratios from 3,321 to 103,536 SCF/STB, gas specific gravity from 0.64 to 0.82 and condensate specific gravity from 0.73 to 0.81. The artificial neural network developed in this study has the best results among all other models with an average absolute error of 6.5%. Graphical and statistical tools have been utilized for the sake of comparing the performance of the new models and empirical models available in literature.