The effects of bio-additives on combustion characteristics and engine performance in an OM355 EU II diesel engine were investigated. Numerical simulations were conducted across a wide range of operating conditions, including engine speed, fuel blends, equivalence ratio, and exhaust gas recirculation (EGR) rates. Key performance metrics, such as torque, power, engine efficiency, indicated specific fuel consumption (ISFC), combustion noise, NOx emissions, and soot behavior, were evaluated. It was found that a reduction in bioethanol content, combined with an increase in the equivalence ratio to 1.2, resulted in a significant improvement in Brake Mean Effective Pressure (BMEP). Furthermore, an increase in soybean methyl ester (SME) content in the fuel blend was observed to reduce combustion noise by alleviating sharp pressure gradients. Higher bioethanol content and EGR rates were associated with lower soot production and NOx emissions, with a blend of 50% bioethanol and 10% EGR achieving a 16.7% reduction in NOx emissions compared to diesel fuel with 0% EGR. Additionally, an Adaptive Neuro-Fuzzy Inference System (ANFIS) model was developed to predict combustion characteristics, engine parameters, and exhaust gas emissions. Various machine learning configurations and training algorithms were employed to optimize the model\\\\\\\'s performance. The findings of this study provide valuable insights into the optimization of engine performance and the reduction of emissions through the use of bio-additives.

Keywords