Application of the ANFIS strategy to estimate vaporization enthalpies of petroleum fractions and pure hydrocarbons

The aim of this study was to utilize the adaptive neuro-fuzzy inference system to estimate the vaporization enthalpy of petroleum fractions and pure hydrocarbons. This tool predicts the vaporization enthalpy as function of the specific gravity, molecular weight, and boiling point temperature based on 122 data gathered from the previous published literatures. Moreover, a comparison was carried out between the present model and some popular models. Results from the adaptive neuro-fuzzy inference system model showed its better predictive capability compared to previous models. The obtained values of root mean square error and R-2 were 0.588 and 0.9934, respectively. This tool is simple to apply and can be of massive evaluation for petroleum engineers to have a great approximation of vaporization enthalpy of pure hydrocarbons hydrocarbon fractions.