Research On Transient Condition Air Fuel Ratio Control Method For Electronic Fuel Injection Gasoline Engine

The electronic fuel injection gasoline engine and three-way catalyst converter is usually applied to control the exhaust emission of gasoline engine in order to satisfy the strict emission regulation. When the fact air fuel ratio is near to the theoretical air fuel ratio, the catalytic converter can be worked more effectively. The gasoline engine is a system of non-linearity and of much perturbation motion, many parameters are always changed with the engine's output power and rotate speed and other different conditions. It is very difficulty to be controlled the air fuel ratio under transient condition. But during the transient process when the fuel is induced into the intake manifold, fuel flow evaporation dynamics and the fuel film is formed on the manifold wall because of the fuel flow dynamics, which affects the control precision of air fuel ratio. Above all, solving the problem of air fuel ratio control during transient condition to make the three way catalyst converter working in the ideal air fuel ratio is the important way to reduce the emission under transient condition.The comprehensive analysis of air-fuel ratio control method is given in this paper. Several methods applied to the air-fuel ratio control are presented respectively, such as the PID control based on classical theory and intelligence control theory and so on, with which the application and developing trend of air fuel ratio is also analyzed. Under the environment of SIMULINK, a simulation model based on Hendricks mean value engine model is built up, and the fuel flim characteristic dynamic of the intake pipe is also analyzed in this paper. A method of airflow forecast under transient conditions based on transient parameter information fusion and BP neural network is presented in this paper; the topological structure of BP neural network is also established. The model is trained and simulated by using experiment data in the acceleration and deceleration condition of gasoline engine. The results show that this method can accurately forecast the engine induction airflow under transient condition and eliminate the lagging characteristic of the airflow sensor. A model of forecasting air fuel ratio based on radial basis function neural network is provided in this paper and the accuracy of air fuel ratio model is compared with different topology structure of neural network. It is showed that the air fuel ratio model based on neural network can be accurately predicted the air fuel ratio under transient condition from the simulation result.