Experimental Investigation and Prediction of Performance, Combustion, and Emission Features of a Diesel Engine Fuelled with Pumpkin-Maize Biodiesel using Different Machine Learning Algorithms

The current study examines the usage of biodiesel as a diesel substitute that is produced through transesterification pumpkin and maize with addition diethyl ether (DEE) additive. Pumpkin-maize (PM) (DEE), well their blends 10%, 20%, 30%, 40%, 50% diesel, were used in performance, combustion, emission examinations under various load conditions. According to experimental findings, adding 5 ml DEE boosts BTE by 31.91 percent (B20 blend) compared diesel. While equivalent BSFC decreases 9.519%. NO dropped 34.91 at peak loads, HC emissions augmented 32.43%, smoke opacity improved 27.24%. To enhance engine features emphasises precise mix proportions PM addition. Using ANN, BTE, predicted R2 values 0.93 0.95, respectively. As can be observed, value for ANN model was almost one, suggesting models had better predictive power than other machine learning (ML) models.