Application of Artificial Neural Networks for prediction of Natural Gas Mixtures
In this paper a new method based on the Artificial Neural Network (ANN) for prediction of Natural Gas Mixture Water Content is presented. The dehydration of natural gas is very important in the gas processing industry, for design of facilities for the production, transmission, and processing of natural gas. It is necessary to remove water vapor present in a gas stream that may cause hydrate formation at low-temperature conditions that may plug the valves and fittings in gas pipelines. In addition, water vapor may cause corrosion difficulties when it reacts with hydrogen sulfide or carbon dioxide commonly present in gas streams. Thus, it is important to review the available data for mixtures and examine the accuracy of the methods for predicting the water content of sour gas. We compared our results with other methods and this comparison shows the efficiency of ANN method for prediction of water content.