Prediction of a gasoline engine performance with artificial neural network

Abstract

This study deals with artificial neural network (ANN) modeling of a gasoline engine to predict the brake specific fuel consumption, effective power and exhaust temperature of the engine. To acquire data for training and testing the proposed ANN, a four-cylinder, four-stroke test engine was fuelled with gasoline having operated at different engine speeds and torques. Using some of the experimental data for training, an ANN model based on standard back-propagation algorithm for the engine was developed. Then, the performance of the ANN predictions were measured by comparing the predictions with the experimental results. Engine speed, engine torque, fuel flow rate, intake manifold mean temperature and cooling water inlet temperature have been used as the input layer, while brake specific fuel consumption, effective power and exhaust temperature have also been used separately as the output layer. It is shown that R2 values are about 0.99 for the training and test data; RMS values are smaller than 0.02; and MEP are smaller than 2.7% for the test data. This study shows that, as an alternative to classical modeling techniques, the ANN approach can be used to accurately predict the performance, temperature and other parameters of internal combustion engines.