estimating onset of precipitation of dissolved asphaltene in the solution of solvent+precipitant using artificial neural network technique
Résumé
Asphaltene precipitation is traditionally modeled using polymer solution theories or cubic equations of state. We propose another approach based on artificial neural network technique to model onset of precipitation of dissolved asphaltene in the solution of solvent + precipitant. A mathematical model based on feed-forward artificial neural network technique, which takes advantage of a modified Levenberg-Marquardt optimization algorithm, has been used to model onset of precipitation of dissolved asphaltene in the solvent + precipitant solution. The experimental data reported in the literature have been used to develop this model. The acceptable agreement between the results of this model and experimental data demonstrates the capability of the neural network technique for estimating onset of precipitation of dissolved asphaltene in the solution of solvent + precipitant.