Development of artificial neural network and response surface methodology model to optimize the engine parameters of rubber seed oil - Hydrogen on PCCI operation

Identifying the suitable alternative fuel and optimum blend concentration for diesel engine combustion is critical as most biodiesel emits excess smoke and has a lower thermal efficiency due to its high viscosity and carbon residue. In the previous work, rubber seed oil was tested in a single-cylinder diesel engine, and its performance and emission results were compared with those of pure diesel, an RSO-diesel (70:30 by volume) blend, RSOmethyl ester, RSO-diethyl ether, RSO-ethanol, and RSO-hydrogen in a dual fuel operation. The testing was performed at a constant speed of 1500 rpm, with the engine loads varying at 25% step intervals. Results showed that smoke and nitrogen oxides were significantly reduced for RSO, and engine performance was enhanced when RSO was operated with hydrogen and diethyl ether in dual fuel mode. In this study, the experimental results were employed to develop an artificial neural network and response surface methodology model. Brake thermal efficiency, rate of pressure rise, carbon monoxide, hydrocarbon, oxides of nitrogen, and smoke were predicted using response surface methodology and artificial neural network. Though artificial neural network produced the best R2 values (0.87264-0.99929), mean absolute percentage error was relatively lesser in response surface methodology. Thus, the authors conclude that response surface methodology is the best suitable artificial intelligence tool to optimize the engine for accomplishing desired responses.