Performance and Emission Analysis of Rapeseed Methyl Ester on DI Diesel Engine Using Artificial Neural Network

Abstract

In the present work, experiments were carried out on four-stroke, single cylinder, water cooled, constant speed, variable compression ratio (VCR) diesel engine. Experiments are done with the engine being fuelled with DI diesel fuel followed by fuel blends of RME20 (20% rapeseed methyl ester and 80% diesel), RME40 (40% rapeseed methyl ester and 60% diesel) and RME100 (pure rapeseed methyl ester) on volume basis. Performance and emission characteristics of diesel and rapeseed methyl ester (RME) with diesel blends are examined. The engine speed is maintained constant at 1500 rpm at different loads and at compression ratios of 16:1, 17:1 and 18:1. The performance parameters like brake thermal efficiency (BTE), brake-specific fuel consumption (BSFC) and exhaust gas temperatures are measured, and the results are recorded. The emission parameters like carbon monoxide (CO), carbon dioxide (CO2), unburnt hydrocarbons (UHC), nitrogen oxides (NOx) and smoke are measured. The correctness of experimental results is analysed with artificial neural network (ANN). Artificial neural network is a tool to efficiently predict the combustion, performance and emission characteristics by using measured data. Artificial neural network toolbox in MATLAB software is used for simulation of engine parameters. The coefficient of determination R2 values is in the range of 0.942–0.990.