Experimental and machine learning‐based environmental performance optimization of M ahua biodiesel using green‐synthesized TiO 2 nano‐additives in compression ignition engines

Abstract

Abstract

Abstract The growing need for sustainable and low‐emission energy has enhanced the studies on biodiesel and enhanced methods of combustion. This paper explores the performance, emission properties, and optimization of a compression‐ignition engine fuelled by Mahua biodiesel (B20) combined with green‐synthesized TiO 2 nanoparticles (50, 100 and 150 ppm). Experiments on engines were carried out in different load conditions to assess brake thermal efficiency (BTE), brake specific fuel consumption (BSFC), exhaust gas temperature and emissions (CO, HC, and NO x ). Findings show that the addition of nanoparticles substantially enhances the combustion performance of the mixture with the highest BTE of 31.8 with B20Ti100 blend, which is a 6.7% increment compared to the initial B20 blend. BSFC reduced to 0.29 kg/kWh, which means that it is more fuel efficient. At full load, emission analysis revealed a decrease in CO (0.18% vol) and HC (27 ppm). The artificial neural network (ANN) model was found to have high predictive accuracy ( R 2 >0.98), and the genetic algorithm (GA)‐based optimization established the 100 ppm TiO 2 at 80% engine load as the optimum operating point. The combination of synthesis of green nanoparticles, experimental validation, and data‐driven optimization offers a promising avenue to enhance the performance of bio‐diesel engines and decrease environmental impact.