Predictive modeling and optimization of SI engine performance and emissions with GEM blends using ANN and RSM

The study employed an Artificial Neural Network (ANN) to predict the performance and emissions of a single-cylinder SI engine using blends of Gasoline, Ethanol, and Methanol (GEM) ranging from E10 to E50 equivalence, achieving less than 5% error compared to experimental values. Furthermore, Response Surface Methodology (RSM) was utilized to optimize the engine's performance, identifying the optimal operating conditions of 2992.9 rpm engine speed and an E20-equivalent GEM blend. Under these conditions, the engine exhibited a brake thermal efficiency (B_The) of 34.63%, a brake specific fuel consumption (BSFC) of 243.7 g/kW-hr, and minimal emissions of 1.5% CO, 108.13 ppm HC, and 1211.8 ppm NO_x, with an overall desirability of 0.820, indicating a highly favorable combination of performance and emissions characteristics.