Prediction of Sour and Natural Gases Compressibility Factor Using an Robust Modeling Approach

Compressibility factor (z-factor) values of natural gases plays an important role in most petroleum and chemical engineering calculations. The main approach to achieve z-factor values are laboratory experiments. Necessity arises when there is no available experimental data for the required composition, pressure and temperature conditions. Therefore, searching for a quick and accurate method for prediction of compressibility factor is inevitable. In this communication, a novel intelligent and reliable model for prediction of z-factor values of natural gases, sour reservoir gases and pure substances is introduced. The model works based on artificial neural network approach and input parameters of the developed model are pseudo reduced temperature and pressure. To evaluate the performance and accuracy of this model, statistical and graphical error analyses were used simultaneously. Moreover, comparative studies have been conducted between this model and nine empirical correlations and equations of state. The obtained results demonstrated that the proposed ANN model is more robust, reliable and efficient than the existing correlations and equations of state for the prediction of z-factor of sour and natural gases. Besides, the analysis of variance illustrated that the pseudo reduced temperature has the greatest impact on the prediction of sour and natural gas compressibility factor.

Keywords:

Sour and natural gases , Intelligent approach , Statistical and graphical error analyses , Analysis of varianc