SUMMARY
The purpose of internal combustion engines is the production of mechanical power from the chemical energy contained in the fuel. Internal combustion engines can be classified into spark ignition (S.I) engine which is the focus of this work and compression ignition engine. S.I engine exhaust gas emissions which consist of oxides of nitrogen (NOX), carbon monoxide (CO) and unburned hydrocarbons (HC) are a major source of urban air pollution. This work investigated the effects of exhaust gas recirculation (EGR), engine speed and engine load on performance and exhaust gas emissions of spark ignition engines. Eleven S.I engine parameters were considered in this work which was divided into three input parameters and eight output parameters. The effects of variations in the input parameters on the output parameters were simulated using artificial neural network software implemented in MATLAB 7.9 environment developed by the authors. From the results obtained, it can be shown that NOX emissions reduced significantly with increase in EGR level while CO and HC emission increased moderately. Specific fuel consumption increased slightly with increase in EGR level while the other four performance parameters reduced with increase in EGR. It can be concluded from this work that for improved performance and low exhaust gas emissions, S.I engines should be operated at low levels of EGR.