Artificial neural network model to predict the performance of a diesel power generator fueled with biodiesel

Alternative fuels are intensively investigated for the replacement of the diesel fuel. Today the diesel power generators are mostly used in the various industrial companies in Iran. Therefore, it is necessary to estimate the level of performance of the diesel power generators fueled with biofuels. For the first time, in this study, the prediction of the performance of a diesel power generator model CAT3412 is carried out for different neural networks to define how the inputs affect the outputs using the biodiesel blends produced from waste cooking oil. Diesel fuel, B100, and biodiesel blends with diesel fuel, which are B20, B50, and B80, were used to measure the engine performance for different engine loads at the rated engine speed. In this paper, artificial neural network models are proposed for the prediction of brake power, brake torque, BTE and BSFC. The coefficient of multiple determination values are found to be above 0.95 for all the models. It is evident that the ANN models are reliable tools for the prediction of the performance of diesel power generator.