Prediction of spark ignition engine performance responses fueled with fusel oil/gasoline blends by artificial neural network

In the present study, performance parameters of a single-cylinder, air-cooled spark ignition (SI) engine using fusel oil-gasoline fuel blends were predicted by artificial neural network (ANN). The SI was operated with gasoline/fusel oil (10% and 20%) at different load (1000, 2000, 3000, 4000, 5000, 6000, 7000 8000 Watt) compression ratios (8.00, 9.12 10.07) to obtain data essential create ANN model. constructed model, brake thermal efficiency (BTE) specific consumption (BSFC) are chosen as output parameters, while load, ratio (CR) input factors. 75% test results employed train ANN. model determined comparing it produced from part not used for training. According found data, estimated such BTE BSFC an overall regression coefficient (R) 0.99384. Simultaneously, mean absolute percentage error (MAPE) 5.027% 7.847% BSFC, respectively. When experimental compared responses, is that close rate less than 5%.