BP Neural Network PID Variable Pressure Control of Airborne Pump Source

Supply pressure control of the aircraft hydraulic pump is of great importance. However, the pressure control system of variable displacement axial piston pumps is significantly affected by fast changing, unknown loads and time-varying parameters. In the present paper, PID control strategy based on BP neural network was proposed to improve the tracking performance of the piston pump outlet pressure. First, the working principle and the mathematical model of the aircraft variable pressure hydraulic system are described. Then the architecture of the BP neural network and the structure of the PID controller are established. In this control strategy, the PID controller parameters kp, ki, kd can be adjusted online through the neural network in order to achieve an excellent control effect. Finally, simulation results demonstrate that there is a good supply pressure tracking performance under the proposed control strategy.