Proposing a modified mechanism for determination of hydrocarbons dynamic viscosity, using artificial neural network

Abstract

In this study, to have an accurate approximation of dynamic viscosity, radial basis function artificial neural network (RBF-ANN) is employed and developed for normal alkanes. This is done by considering the distinct number of carbons in n-alkanes, certain temperatures, and different pressures. Moreover, in order to train and test the predicting model, a databank of 228 experimental data is gathered from reliable sources in the literature. As a result, training and testing coefficient values are measured 0.99739 and 0.99051; consequently, the robustness and accuracy of RBF-ANN in providing an estimation of n-alkane viscosity is confirmed by graphical analysis and determined indexes.

Topics & Concepts