10th November 2022
A machine learning model forpredicting the thermophysicalpropertiesat a wider range of temperature (300 to 700 K)that are essential for spray, combustion, and emission modeling is developed in this work.The modeluniquenessis that, itcanpredict the variouspropertiesof biodiesel fuelsbased on only their composition without using the complex analytical correlations.A good agreement isobserved for the model results with a maximum mean absolute percentage error of 10 %. Hence,the model is robust in terms of the fuelproperty predictions over abroad range of temperature.