Abstract
Existing electronic engine control (EEC) system, usually control air/fuel ratio and spark timing under different operating condition. In this paper, a method use neural network in optimization air/fuel ratio for a S.I engine is described. The investigation has addressed the definitions of a suitable back -propagation network, the engine static bench test to get the data for neural network training, and the definitions of objective function for the air/fuel ratio optimization under different operation condition. The results presented demonstrate that a small number of test data are sufficient to optimize the air/fuel ratio under different engine rotate speed and throttle position. By applying the neural network, the result of air/fuel optimization for a CA6102 automotive gasoline engine is proposed, and the engine performance is improved.