Design of PID Control based on BP Neural Network for Double-holding Process System

The control process of liquid level in double-holding water tank (DHWT) has the characteristics of multiple interference, great inertia and strong nonlinearity, its control performance optimization and parameter setting are extremely difficult. In aspect of the sensitivity, system stability and parameter setting, traditional PID control are inadequate. Therefore, this paper presented a kind of self-learning, self-optimized PID control based on back propagation (BP) neural network, it can make up the deficiency of traditional PID. The simulation results show that, compared with traditional PID, the proposed method can improve the performance index of the DHWT system.