Research On Neutral Network Control For Rail Pressure Of High Pressure Common Rail Diesel Engine

High-pressure Common Rail System(HCRS) is the best injection system for its accurate control in pressure injection, quantity injection, timing and injection rate. It can meet the requirement of energy-saving and reducing pollution, and delegates the developing tendency of diesel engine fuel injection technology. But, HCRS is hard to be controlled because it is a complex nonlinear time-varying system combinated mechanical electric hydraulic, its parameters would change with time and environment for the disturbance from noise and load. So, one of the most important factors which decide the quality of HCRS is the choice of control mode.PID can't achieve satisfactory control results from the results of control HCRS. Neural Network has self-learning self-organization and leaning abilities as a newly arising intelligent control method. The combination of the neural network with the PID is a efficient measure of solving PID controller's defects.The text has discussed the structure and algorithm of back propagation neural network adjusting PID controller and the application in HCRS. Carried on simulation to traditional PID controller and neural network PID controller, simulation result indicated that use neural network go on after improving raising robustness and dynamic characteristic of system to routine PID controller, the systematic control result has been improved. The neural network PID controller's effect which worked in rail pressure has been proved.