Modeling of an SI engine performance parameters and emissions using bioethanol-gasoline blends by genetic programming

In this paper، a model is described to predict performance parameters and emissions of a spark ignition (SI) engine using genetic programming (GP). To acquire data for training and testing of proposed GP، a four-cylinder engine was fueled with ethanol-gasoline fuel blends. The pure gasoline fuel was blended with various percentages of bioethanol (0، 5، 10، 15 and 20%)، and the engine brake power، the torque and exhaust emissions (CO، HC، CO2 and NOX) were measured at different engine speeds and loads. Experimental results showed that as the ratio of the ethanol fuel was increased in the blend، CO and HC emissions were decreased but the brake power، the torque، CO2 and NOX were increased. Numerous runs were performed with the GP model and the performance of developed equations was evaluated. Optimum models were selected according to statistical criteria of the root mean square error (RMSE) and the coefficient of determination (R2). Simulation results demonstrated that the GP model was a powerful tool to predict engine pollutant emissions.