Neural Network Approach for Prediction of Asphaltene precipitation and comparison it with Flory-Huggins model in crude oil

Asphaltenes are problematic substances for heavy-oil upgrading processes. Deposition of complex and heavy organic compounds, which exist in petroleum crude oil, can cause a lot of problems. In this work an Artificial Neural Networks (ANN) approach for estimation of asphaltene precipitation has been proposed. Among the various training algorithms, the ANN, Radial Basis (RBF) method had the best prediction performance and was used for prediction of the asphaltene precipitation. The experimental data of two samples typical crude oil were pre-scaled and used for training of Artificial Neural Networks. The ANN has been trained with 2/3 of data set and 1/3 of samples have been used for testing the predictions of NN. The results show ANN capability to predict the measured data. ANN model performance is also compared with Flory-Huggins model. The comparison confirms the superiority of the ANN model.

کلیدواژه ها:

Keywords: Asphaltene ، Precipitation ، Artificial Neural Networks ، Flory-Huggins model ، crude oil