Study of PID neural network for hydraulic system

This paper provides an adaptive PID controller based on back propagation (BP) neural network applied to pressure control of hydraulic system. The controller has many advantages like that more convenient in parameter regulating, better robust, more independence and adaptability in the hydraulic system. According the requirements of system performance, this paper discussed the corresponding learning algorithm and implementation method, which the BP neural network can auto-adjust its weights to vary k_p, k_i and k_d of PID controller. Improved algorithm of BP neural network also was proposed to speed up convergence and deduce concussion of neural network. The simulation results of the pressure control of hydraulic system by using adaptive PID controller based on BP neural network show that it can get better control characteristics and adaptability, strong robustness in the nonlinear and time vary hydraulic system.