Prediction Based On Bp Neural Network Model Of The Engine Idle Speed Control

Mathematical model establishment in nonlinear system such as automobile engine is still very hard. Artificial neural network theory brings to us a new method in nonlinear system identification. On principle of system identification theory, this paper uses 2JZ-GE petrolic computer experimentation system to get the required idle rotate speed data. By using the collection data in training the neural network, this paper establishes the proper engine idle speed neural network model. Also, the neural network training algorithm, network structure and training result validation problems are dicussed here.Predict control has the virtue of simple algorithm and stronger robust. So, it is suit for controlling the nonlinear system such as engine which has pure time delay and open-loop gradually stabilization characters. By using the founded neural network model and DMC predict control algorithm, simulation research has been completed on the idle speed control in this pape. The result shows that the DMC algorithm is adaptable for the engine idle speed control.