The researches on Wankel engines are very rare and considered new in modelling and prediction. Therefore this study deals with the artificial neural network (ANN) modelling of a Wankel engine to predict the power, volumetric efficiency and emissions, including nitrogen oxide, carbon dioxide, carbon monoxide and oxygen by using the change of mean effective pressure, intake manifold pressure, start of ignition angle and injection duration as inputs. The experiment results are taken from a research which is performed on a single-rotor, four stroke and port fuel injection 13B Wankel engine. The number of data which are taken from experimental results are scarce and varied in six different data set (for example; mean effective pressure, from 1 to 6 bar) at 3000 rpm engine speed. The standard back-propagation (BPNN) Levenberg-Marquardt neural network algorithm is applied to evaluate the performance of middle speed range Wankel engine. The model performance is validated by comparing the prediction data sets with the measured experimental data. Results approved that the artificial neural network (ANN) model provided good agreement with the experimental data with good accuracy while the correlation coefficient R varies between 0.79 and 0.97.

Mixture formation in port fuel spark ignition engines is one of the most im-portant parameters, which affect combustion and emissions. In this study, the ef-fects of different injection start timings and some other port fuel injection (PFI) parameters on the performance and emissions of a water cooled and single cylin-der spark ignition engine were examined experimentally. The experiments were performed at different engine speeds (1200 and 1500 rpm for effect of injection pressure and 1500 rpm for changing injection timings) and different engine loads (3 bar and 5 bar for injection pressure and 1 bar and 5 bar for start of injection). The start of injection was chosen according to intake pressure measurements. The experiment results showed that brake specific fuel consumption (BSFC) and total hydrocarbon (THC) emissions are increased by the increase of the injection pressure. Because with the increase of injection pressure, the fuel can reach the intake manifold wall or intake valve. Therefore, the fuel enters the cylinder as a droplet. Different start of injection experiments showed that injection times have an effect on emissions and performance. The minimum brake specific fuel con-sumption and THC values were obtained at -243 °CA value of injection start. The twice injection in one cycle increased brake specific fuel consumption and THC emissions.

In this study, an electronic control unit was designed and developed for a single rotor Wankel engine. The code was written the Arduino IDE. An interface is designed in Visual Studio for computer control of a single rotor test engine. Thanks to the control unit, the injection advance, injection duration, engine speed, dwell time and ignition advance were controlled. In the hardware part, firstly solid state relay was used for switching, and then a MOSFET circuit was tested. It was observed that the ignition and spraying signals received from the oscilloscope for both switching came regularly and continuously at different speeds (600, 1000 and 3000 rpm). Afterwards, according to the results obtained with the oscilloscope and high speed camera, there was no delay in opening time of the injector with the solid state relay. However, there was 0.6 milliseconds delay in closing time of it. This situation caused the engine to run erratically and unstable at high speeds. In the circuit established with Mosfet, there was no delay at the opening and closing times of the injector. As a result, it was concluded that it would be more appropriate to use the circuit designed with MOSFET in the control unit.