Engine pollutants have been a significant source of concern in most countries around the world because they are one of the major contributors to air pollution, which causes cancer, lung disorders, and other severe illnesses. The need to reduce emissions and its consequences has prompted studies into the emission profile of internal combustion engines running on particular fuels. To this end, this study employed the power of Artificial Neural Networks (ANNs) to investigate the impact of injection timing on the emission profile of Compression Ignition Engines fuelled with blends of Tropical Almond Seed Oil based-biodiesel; by conducting a series of experimental tests on the engine rig and using the results to train the ANNs; to predict the emission profile to full scale. Blend percentages, load percentages, and injection timings were used as input variables, and engine emission parameters were used as output variables, to train the network. The results showed that injection timing affect emission output of CI engines fuelled with Tropical Almond Oil based biodiesel; and for the emission pattern to be friendly, injection timing must rather be retarded and not advanced. The results also showed that for different engine emission parameters, there is a strong association between the ANN output results and the actual experimental values; with mean relative error values less than 10%, which fall within the acceptable limits. For emission of CI engines fuelled with Tropical Almond Oil based biodiesel to be friendly in pattern, injection timing must be relatively retarded. The study also concluded that Artificial Neural Network (ANN) is a reliable tool for predicting Compression Ignition Engines emission profiles.
Investigation of the Effects of Piston Geometry and Combustion Process Parameters on Engine Performance of Methane Fuelled Compression Ignition Engines with Kriging Method