Third-generation algae biofuels, made from biomass, are a promising renewable fuel due to their low carbon footprint. In internal combustion engines, it hinders combustion and performance. This study aims to improve engine efficiency by blending algae biodiesel with nano additives. First, Grey-Taguchi optimization is used to find the best blend, compression ratio, load, EGR, and nano-additive concentration for key performance
indicators. The Grey-Taguchi method efficiently analyses complex parameters and reduces experiments, saving time and resources. Following experimental data, an Artificial Neural Network (ANN) model predicted future emissions and performance. The ANN model was trained with 25 observations for 20% and 30% biodiesel blends. The ANN model predicted engine behavior with over 90% accuracy and was effective. The study shows that algae biodiesel and nano-additives can improve engine performance and provide a reliable projection method. B20CV + 100 ppm ZnO improved BTE and BP by 4.2% and 3.8% over diesel. The BSFC dropped 5.1%, showing better fuel use. However, nanoparticle agglomeration increased NOx emissions. Due to its lower calorific value, B30CV + 100 ppm ZnO reduced BTE by 6.5% and increased BSFC by 7.3%. The developed ANN model predicted performance and emissions with over 90% accuracy, with minor NOx deviations due to combustion variation. This novel study uses Grey-Taguchi optimization and ANN modelling to assess and predict engine performance and emissions from nanoparticle-enriched algae biodiesel blends.