Applying Neural Networks to PID Controllers for Time-Delay Systems

Generalized PID neural network (GPIDNN) has recently received more attention in industry application. To investigate the control of long time-delay systems with GPIDNN control system, both the structure and the algorithm were presented in this paper, the real-time simulation to a main steam temperature control system was also carried out. The results show that GPIDNN is less sensitive to variation in the time-delay in comparison of conventional PID control system, it has short transition time and little over-adjust as well as ideal control quality. The results obtained during the present study indicate that GPIDNN has favorable control ability with self learning and self adapting; it is suitable substitute for conventional PID controllers for long time-delay systems