Simulation Study of PID Neural Network Temperature Control System in Plastic Injecting-Moulding Machine

PID (proportional, integral and derivative) neural network is a special neural network in which the neurons have proportional, integral and derivative input-output functions and was first given by the author in 1997. The simulation about a three-stage heater in a plastic injection machine was introduced in this paper. The temperature control system of the plastic injection machine is a strong coupled multivariable system and the characteristics of the system are analyzed in the paper. The algorithms of PID neural network are given, the VB program of the back propagation algorithm was introduced and the simulation results are shown. The results prove that the PID neural network has perfect decoupling and self-learning control performances.