Estimation of sour natural gas water content

Abstract

In this paper a new method based an artificial neural network (ANN) for prediction of naturalgas mixture watercontent (NGMWC) is presented. H2S mole fraction, temperature, and pressure have been input variables of the network and NGMWC has been set as network output. Among the 136 data set 80 data have been implemented to find best ANN structure. 56 data have been used to check generalization capability of the best trained ANN. Comparisons show average absolute error (AAE) equal to 1.437 between ANN estimations and unseen experimental data. ANNs also have been compared with two commonly used correlations in gas industry. Results show ANN superiority to correlations. Especially in higher hydrogen sulfide content in spite of ANN good predictions there was considerable deviation between experimental data and common correlations. The proposed ANN model is able to estimate NGMWC as a function of hydrogen sulfide composition up to 89.6 mol%, temperatures between 50 and 350 °F and pressure from 200 up to 3500 psia.