Identification research on improved PID neural network and its application

Abstract

PID neural network (PID-NN) is a new type of dynamic feed-forward network which combines neural network with PID control strategy. It performs a perfect function in process control with the merit of both general PID controller and neural network. In this paper, the concepts of variable integral and partial differential are introduced in the design of hidden-layer of PID-NN to improve the capabilities of neurons. The structure of system identification is analyzed, and the results of simulation with field data of wet FGD indicate the validity and superiority of this improved modeling approach.