This study details the artificial neural network (ANN) modelling of a diesel engine to predict the torque, power, brake-specific fuel consumption and pollutant emissions, including carbon dioxide, carbon monoxide, nitrogen oxides, total hydrocarbons and filter smoke number. To collect data for training and testing the neural network, experiments were performed on a four cylinder, four stroke compression ignition engine. A total of 108 test points were run on a dynamometer. For the first part of this work, a parameter packet was used as the inputs for the neural network, and satisfactory regression was found with the outputs (over ~95%), excluding total hydrocarbons. The second stage of this work addressed developing new networks with additional inputs for predicting the total hydrocarbons, and the regression was raised from 75 % to 90 %. This study shows that the ANN approach can be used for accurately predicting characteristic values of an internal combustion engine and that the neural network performance can be increased using additional related input data

In this study, a four stroke four cylinder direct injection CI engine was run using three different injection pressures. In all measurements, the fuel quantity per cycle, the pre injection and main injection timing, the boost pressure and the engine speed were kept constant. The motor tests were performed under 130, 140 and 150 MPa rail pressure. During the theoretical part of the study, combustion, emission, energy and exergy analysis were made using the test results. An increase in the injection pressure increases combustion efficiency. The results show that combustion efficiency is not enough by itself, because the increase in the power need of the injection pump, decreases the thermal efficiency. The increase in the combustion temperature, increases the cooling loss and decreases the exergetic efficiency. In addition, the NO_x emissions increased by 12% and soot emissions decreased 44% via increasing injection pressure by 17%. The thermal and exergetic efficiencies are found inversely proportional with injection pressure. Exergy destruction is found independent of the injection pressure and its value is obtained as ~6%.