Chemical Engineering
Saeed Mohammadi; Mohammad Amin Sobati; Mohammad Sadeghi
Abstract
Dilution is one of the various existing methods in reducing heavy crude oil viscosity. In this method, heavy crude oil is mixed with a solvent or lighter oil in order to achieve a certain viscosity. Thus, precise mixing rules are needed to estimate the viscosity of blend. In this work, new empirical ...
Read More
Dilution is one of the various existing methods in reducing heavy crude oil viscosity. In this method, heavy crude oil is mixed with a solvent or lighter oil in order to achieve a certain viscosity. Thus, precise mixing rules are needed to estimate the viscosity of blend. In this work, new empirical models are developed for the calculation of the kinematic viscosity of crude oil and diluent blends. Genetic algorithm (GA) is utilized to determine the parameters of the proposed models. 850 data points on the viscosity of blends (i.e. 717 weight fraction-based data and 133 volume fraction-based data) were obtained from the literature. The prediction result for the volume fraction-based model in terms of the absolute average relative deviation (AARD (%)) was 8.73. The AARD values of the binary and ternary blends of the weight fraction-based model (AARD %) were 7.30 and 10.15 respectively. The proposed correlations were compared with other available correlations in the literature such as Koval, Chevron, Parkash, Maxwell, Wallace and Henry, and Cragoe. The comparison results confirm the better prediction accuracy of the newly proposed correlations.
Bizhan Khosronezhad Gheshlaghi; Mohammad Reza Dehghani; Hossein Parhizgar
Abstract
In this work, artificial neural network (ANN) was utilized to develop a new model for the prediction of the kinematic viscosity of petroleum fractions. This model was generated as a function of temperature (T), normal boiling point temperature (Tb), and specific gravity (S). In order to develop the new ...
Read More
In this work, artificial neural network (ANN) was utilized to develop a new model for the prediction of the kinematic viscosity of petroleum fractions. This model was generated as a function of temperature (T), normal boiling point temperature (Tb), and specific gravity (S). In order to develop the new model, different architectures of feed-forward type were examined. Finally, the optimum structure with three hidden layers was selected. The optimum structure had five, four, and two neurons in the first, second, and third layers respectively. To prevent over-fitting problem, 70% of the experimental data were used to train and validate the new model and the remaining data which did not participate in learning process was utilized to test the ability of the new model for the prediction of the kinematic viscosity of petroleum fractions. The results showed that the predicted/calculated and experimental data are in good agreement. The average absolute relative deviation (AARD) of the new model was 1.3%. Finally, the results were compared with an Eyring-based model (Soltani et al.’s work); it was shown that, based on the reported results by the authors, the accuracy of both model were in the same order.
