Experimental investigation and Neural network based prediction of performance and Emission characteristics of a 4 stroke c.!. enginewith wco as biodiesel
暂无分享,去创建一个
Biodiesel is a nonpetroleum-based fuel defined as fatty acid methyl or ethyl esters derived from vegetable oils or animal fats and it is used in diesel engines and heating
systems. However, the high cost of biodiesel is the major obstacle for its commercialization. The biodiesel produced from vegetable oil or animal fat is usually more expensive than petroleum-based diesel fuel from 10 to 50%. Moreover, during 2010, the prices of virgin vegetable oils have nearly doubled in relation to the early 2000. Compared to neat vegetable oils, the cost of waste vegetable oils is anywhere from 60% less to free, depending on the source and availability. This paper deals with potential of using waste cooking oil (WCO) as a substitute for a petroleum-based diesel tuet. The engine performance studies were conducted on a single cylinder fourstroke water-cooled compression ignition engine connected to an eddy cuttent
dynemometer. Experiments were conducted for different percentage of blends of WCO with diesel at various compression ratios. Engine performance parameters
were studied at different loads for the above experiments. Exhaust emissions from the engine were also noted. Artificial Neural Networks (ANN) are a widely used
mathematical technique for prediction and classification based applications. In this study ANNs are used to predict the Engine performance and emission characteristics
of the engine_ To train the network, compression ratio, blend percentage, percentage load, were used as the input variables where as engine performance parameters like
Brake thermal efficiency, Brake Specific Energy consumption, Exhaust gas temperature with engine exhaust emissions such as NOx, smoke, CO,UBHC values
were used as the output variables. Backpropagation algorithm was used to train the network. ANN results showed that there is a good cottetetion between the ANN
predicted values and the desired values for various engine perfonnance values and exhaust emissions. The R' values for the predicted and the target values for all the variables were vel)' close to 1 and the relative mean error values were within 10 percent.