Experimental evaluation and neural network modelling of reactivity-controlled compression ignition engine using cashew nut shell oil biodiesel-alumina nanoparticle blend and gasoline injection

The current desire is for enhanced combustion techniques that improve engine efficiency while successfully reducing emissions. Reactivity controlled compression ignition (RCCI) combustion encompasses the ability to increase fuel efficiency and decrease oxides of nitrogen emissions compared to conventional compression ignition (CI) combustion. This study presents a novel investigation that focuses on the capabilities of the RCCI engine, utilizing a unique combination of gasoline and diesel blended with cashew nut shell oil biodiesel (CNSOB) and the addition of aluminum oxide (Al2O3) nanoparticles. CNSOB extracted from waste shell has an oil content of 30–35 wt% yield. The cost of the oil range between is ₹. 40–50 in India. The engine operates on a blend of gasoline, known for its low reactivity, and diesel blended with CNSOB, a renewable and environmentally friendly alternative to diesel. The effects of varying proportions of the blend (B0, B50, and B100) and the addition of Al2O3 nano additive (25 and 50 ppm) on the efficiency and emissions of RCCI combustion are comprehensively analyzed experimentally. The results reveal that RCCI combustion significantly improves engine performance compared to compression ignition engines. A 2% increase in maximum in-cylinder pressure indicates improved combustion efficiency. Furthermore, fuel economy is improved by up to 2% due to increased engine brake thermal efficiency (BTE). Further, nitrogen oxide (NOx) emissions are reduced by up to 54% during RCCI combustion, demonstrating its potential for reducing pollution. Utilizing CNSOB biodiesel results in a 50% reduction in hydrocarbon (HC) emissions as well as a 17% reduction in carbon monoxide (CO) emissions. This indicates improved air quality and reduces environmental pollution. The incorporation of Al2O3 nano additives into the RCCI engine results in a 5% reduction in brake specific energy consumption (BSEC), showing better engine energy efficiency. Based on the results of the investigation, a neural network framework was developed. The neural network framework was developed to replicate both the efficiency and pollution parameters of the RCCI engine using the experimentally determined relationship between input factors and output parameters. The neural network model was trained using 70% of the available data, and its performance was evaluated by comparison of predictions with the corresponding observations from experiments. The forecast outcomes matched those of the trial, demonstrating the artificial neural network (ANN) models effectiveness and precision in predicting the engine performance and emissions.