Application of ANFIS strategy for prediction of biodiesel production using supercritical methanol

Research for finding alternative fuel sources has been concluded that the renewable fuels such as biodiesel can be used as an alternative to fossil fuels because of the energy security reasons and environmental benefits. In the present study, a modeling study based on statistical learning theory has been investigated by the adaptive neuro-fuzzy interference system (ANFIS) approach for biodiesel production in non-catalytic supercritical methanol (SCM) method. This model has been applied for estimating the biodiesel yield as a function of temperature, pressure, reaction time, and Methanol/oil ratio. The results, the high value of R-squared (0.9978) and low value of absolute deviation (1.14%), support the suggested ANFIS model for being an effective approach for prediction of the biodiesel yield. A comparison between our model and another previous ANN-based model has been also carried out that indicates a great agreement of estimations of both models.