This paper studies the use of adaptive neuro-fuzzy inference system (ANFIS) to\npredict the performance parameters and exhaust emissions of a diesel engine operating on\nnanodiesel blended fuels. In order to predict the engine parameters, the whole experimental\ndata were randomly divided into training and testing data. For ANFIS modelling, Gaussian\ncurve membership function (gaussmf) and 200 training epochs (iteration) were found to be\noptimum choices for training process. The results demonstrate that ANFIS is capable of\npredicting the diesel engine performance and emissions. In the experimental step, Carbon nano\ntubes (CNT) (40, 80 and 120 ppm) and nano silver particles (40, 80 and 120 ppm) with nanostructure\nwere prepared and added as additive to the diesel fuel. Six cylinders, four-stroke\ndiesel engine was fuelled with these new blended fuels and operated at different engine speeds.\nExperimental test results indicated the fact that adding nano particles to diesel fuel, increased\ndiesel engine power and torque output. For nano-diesel it was found that the brake specific fuel\nconsumption (bsfc) was decreased compared to the net diesel fuel. The results proved that with\nincrease of nano particles concentrations (from 40 ppm to 120 ppm) in diesel fuel, CO2\nemission increased. CO emission in diesel fuel with nano-particles was lower significantly\ncompared to pure diesel fuel. UHC emission with silver nano-diesel blended fuel decreased\nwhile with fuels that contains CNT nano particles increased. The trend of NOx emission was\ninverse compared to the UHC emission. With adding nano particles to the blended fuels, NOx\nincreased compared to the net diesel fuel. The tests revealed that silver & CNT nano particles\ncan be used as additive in diesel fuel to improve combustion of the fuel and reduce the exhaust\nemissions significantly.
Loading....