Research of PID Control System Based on Diagonal Recurrent Neural Network

摘要

This paper presents a new optimization variable arguments PID controller based on Diagonal Recurrent Neural Network (DRNN). The parameters of PID controller can be tuned on line, and its learning algorithms are given. Utilizing DRNN and recurrent prediction error algorithm (RPE) is the identification of a controlled plant realized. The simulation results show that this system is reliable, adaptive, fast and robust.