Experimental Study and Prediction of Performance and Emission in an SI Engine Using Alternative Fuel with Artificial Neural Network

Authors : Mustafa Kemal BALKİ, Volkan ÇAVUŞ, İsmail Umut DURAN, Resul TUNA, Cenk SAYİN

Pages : 58-64

Doi:10.18245/ijaet.438048

View : 20 | Download : 7

Publication Date : 2018-04-03

Article Type : Other Papers

Abstract :In this study, firstly, the effect of compression ratio insert ignore into journalissuearticles values(CR);, air excess coefficient insert ignore into journalissuearticles values(AEC); and ignition timing insert ignore into journalissuearticles values(IGT); on the performance and exhaust emissions in a spark ignition insert ignore into journalissuearticles values(SI); engine fueled with pure ethanol was experimentally investigated. The engine tests were conducted for four varied CR, three types of AEC and three different IGT at 2400 rpm, and the performance and exhaust emission of the engine were recorded. The results obtained from the pure ethanol were compared with those of the gasoline. Secondly, the performance and exhaust emission of SI engine for the same test conditions were estimated with a backpropagation artificial neural network insert ignore into journalissuearticles values(ANN); model. The ANN model was created using the C# programming language. The ANN model was trained with the data obtained from the experimental study. The engine torque, brake specific fuel consumption insert ignore into journalissuearticles values(BSFC);, hydrocarbon insert ignore into journalissuearticles values(HC); emission and carbon dioxide insert ignore into journalissuearticles values(CO2); emission were estimated by the backpropagation ANN model. When the experimental data were compared with the predicted values, it was seen that the error percentages of the difference were acceptable. When the results were generally evaluated, it was observed that was improved of the performance and exhaust emissions as using pure ethanol at lowering the IGT and increasing the CR. In addition, it is seen that the ANN model can be used to estimate the performance and emissions of an SI engine using alternative fuels.
Keywords : Artificial neural network, Ethanol, Engine performance, Exhaust emissions