Modeling of vaporization enthalpies of petroleum fractions and pure hydrocarbons using genetic programming

In this work utilizing genetic programming, a new model has been presented for prediction of vaporization enthalpy of petroleum fractions as well as pure hydrocarbons. Using genetic programming enabled us to find a new relation between vaporization enthalpy and thermo-physical properties such as specific gravity, molecular weight and boiling point temperature. The results have been compared with previous models. It has been shown that our model can give better results compared to previous ones. In order to check the predictability of the model, vaporization enthalpy of pure hydrocarbons has been excluded from the learning set, it is worth mentioning that finally the presented model predicted them efficiently, this result shows that it can be utilized for prediction in the case of new hydrocarbon fractions.