The Prediction of Surface Tension of Ternary Mixtures at Different Temperatures Using Artificial Neural Networks

In this work, artificial neural network (ANN) has been employed to propose a practical model forpredicting the surface tension of multi-component mixtures. In order to develop a reliable modelbased on the ANN, a comprehensive experimental data set including 15 ternary liquid mixtures atdifferent temperatures was employed. These systems consist of 777 data points generally containinghydrocarbon components. The ANN model has been developed as a function of temperature, criticalproperties, and acentric factor of the mixture according to conventional corresponding-state models.80% of the data points were employed for training ANN and the remaining data were utilized fortesting the generated model. The average absolute relative deviations (AARD%) of the model for thetraining set, the testing set, and the total data points were obtained 1.69, 1.86, and 1.72 respectively.Comparing the results with Flory theory, Brok-Bird equation, and group contribution theory hasproved the high prediction capability of the attained model.

Keywords:

Surface Tension , Mixtures , Artificial Neural Network