A Comparative Study of Artificial Intelligence Based Models to Predict Performance and Emission Characteristics of a Single Cylinder Diesel Engine Fueled With Diesosenol

Abstract

This study investigates the potential of oxygenated additive (ethanol) on adulterated diesel fuel on the performance and exhaust emission characteristics of a single cylinder diesel engine. Based on the engine experimental data, two artificial intelligence (AI) models, viz., artificial neural network (ANN) and adaptive-neuro fuzzy inference system (ANFIS), have been modeled for predicting brake thermal efficiency (Bth), brake specific energy consumption (BSEC), oxides of nitrogen (NOx), unburnt hydrocarbon (UBHC) and carbon monoxide (CO) with engine load (%), kerosene (vol %), and ethanol (vol %) as input parameters. Both the proposed AI models have the capacity for predicting input–output paradigms of diesel–kerosene–ethanol (diesosenol) blends with high accuracy. A (3–9–5) topology with Levenberg–Marquardt feed forward back propagation (trainlm) learning algorithm has been observed to be the ideal model for ANN. The comparative study of the two AI models demonstrated that ANFIS predicted results have higher accuracy than the ANN with a maximum RANFIS/RANN value of 1.000534.