Accurate prediction of viscosity of mixed oils

Viscosity of mixed oil is an important parameter which is required in transportation and production processes of mixed crude oils. There is no universal and general model for prediction of viscosity of mixed oils at different conditions. Hence, developing simple, accurate and general models for prediction of mixed oil viscosity is of great importance. In this work three computer based models named MLP-NN, PSO-RBF and Hybrid-ANFIS were developed for prediction of viscosity of mixed oils. A number of 513 experimental data covering wide ranges of influencing parameters were utilized to develop the models. The accuracy of predictions of the developed models was examined by using different statistical quality measure approaches as well as comparing their results with predictions of literature models. Results showed that the developed models present accurate predictions and are superior to literature models. The predictions of MLP-NN model were also better than Hybrid-ANFIS and PSO-RBF models.