A mathematical model based on artificial neural network technique for estimating liquid water-hydrate equilibrium of water-hydrocarbon system
Résumé
A mathematical model based on feed-forward artificial neural network technique, which uses a modified Levenberg-Marquardt optimization algorithm, has been developed to estimate the solubility of a pure hydrocarbon hydrate former in pure water being in equilibrium with gas hydrates. More recent and reliable data for three hydrocarbon hydrate formers (methane, ethane, and propane) have been used to train and develop this model. Independent experimental data (not employed in training and testing) have been used to examine the reliability of this technique. The acceptable agreement between the predicted and experimental data demonstrates the capability of the neural network model for estimating the solubility of pure hydrocarbon hydrate formers in pure water being in equilibrium with gas hydrates.