Estimating water content of natural gas mixtures considering heavy hydrocarbons contribution using artificial neural networks

The accurate estimation of the water content of natural gas is the basis for proper equipment design in natural gas processing and transmission facilities. Methods for estimating the water content of natural gas have been reported based on pressure and temperature data, and the concentration of acid gases. This work aims to develop a predictive model based on artificial neural networks (ANN) to estimate the water content of natural gas, considering the contribution of heavier hydrocarbons than methane, commonly present in the rich gases, gas condensates, or liquefied petroleum gases. The novelty of the proposed model is the incorporation of natural gas richness (GPM) as an input parameter for calculating the water content of natural gas, in addition to temperature, pressure, and acid gas equivalent content. Experimental data from the literature is used in the ANN training and validation, with the help of the BigML machine learning platform to perform a multi-layer-feedforward neural network. The ANN performance showed the ability to accurately predict the water content for different gas mixtures (rich, lean, sweet, and sour gases). Comparisons with available models in the literature are performed, showing that the ANN model provides accurate estimations (AAD: < 10%).