Prediction of asphaltene precipitation in crude oil

Abstract Asphaltene 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 this training the back-propagation learning algorithm with different training methods were used. The most suitable algorithm with appropriate number of neurons in the hidden layer which provides the minimum error is found to be the Levenberg–Marquardt (LM) algorithm. ANN's results showed the best estimation performance for the prediction of the asphaltene precipitation. The required data were collected and after pre-treating was used for training of ANN. The performance of the best obtained network was checked by its generalization ability in predicting 1/3 of the unseen data. Excellent predictions with maximum Mean Square Error (MSE) of 0.2787 were observed. The results show ANN capability to predict the measured data. ANN model performance is also compared with the Flory–Huggins and the modified Flory–Huggins thermo dynamical models. The comparison confirms the superiority of the ANN model.

[1]  G. Pazuki,et al.  A modified Flory-Huggins model for prediction of asphaltenes precipitation in crude oil , 2006 .

[2]  A. Gil-Villegas,et al.  Asphaltene Precipitation in Crude Oils: Theory and Experiments , 2004 .

[3]  Gholamreza Zahedi,et al.  A Neural Network Approach for Prediction of the CuO-ZnO-Al2O3 Catalyst Deactivation , 2005 .

[4]  H. Modarress,et al.  Phase behavior of binary mixture of asphaltene + solvent and ternary mixture of asphaltene + solvent + precipitant , 2006 .

[5]  A. B. Bulsari,et al.  Neural Networks for Chemical Engineers , 1995 .

[6]  J. G. Meijer,et al.  Influence of Temperature and Pressure on Asphaltene Flocculation , 1984 .

[7]  Hedia Fgaier,et al.  Artificial Neural Network Identification and Evaluation of Hydrotreater Plant , 2006 .

[8]  Harry Rodríguez-Vallés,et al.  A neural networks method to predict activity coefficients for binary systems based on molecular functional group contribution , 2006 .

[9]  Adnan Sözen,et al.  Investigation of thermodynamic properties of refrigerant/absorbent couples using artificial neural networks , 2004 .

[10]  M. Sahimi,et al.  Asphalt flocculation and deposition: I. The onset of precipitation , 1996 .

[11]  Mohammad R. Riazi,et al.  Physical properties of heavy petroleum fractions and crude oils , 1996 .

[12]  Adnan Sözen,et al.  Formulation based on artificial neural network of thermodynamic properties of ozone friendly refrigerant/absorbent couples , 2005 .

[13]  Martin T. Hagan,et al.  Neural network design , 1995 .

[14]  Ali Elkamel,et al.  Hybrid artificial neural network—First principle model formulation for the unsteady state simulation and analysis of a packed bed reactor for CO2 hydrogenation to methanol , 2005 .