Optimizing Bio-Diesel Combustion and Emissions Through Artificial Intelligence Techniques

The global transition toward sustainable energy has accelerated interest in alternative fuels such as biodiesel, valued for its renewability and environmental advantages. This study investigates the performance and emission characteristics of biodiesel in comparison to conventional diesel, emphasizing the application of Artificial Intelligence (AI) for predictive modeling. Machine learning techniques—including Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Random Forests—are utilized to model key engine parameters such as brake thermal efficiency (BTE), brake-specific fuel consumption (BSFC), and emissions including carbon monoxide (CO), and nitrogen oxides (NOx). The findings reveal that while biodiesel blends tend to produce slightly lower power output, they achieve notable reductions in CO and hydrocarbon emissions, with a corresponding increase in NOx levels. The AI models demonstrate strong predictive capabilities across diverse operating conditions, facilitating the optimization of fuel blends and engine settings. This integration of AI into biodiesel research presents a promising pathway for enhancing the environmental and operational performance of internal combustion engines.