板形板厚综合系统的前馈解耦神经网络预测控制方法

A NEURAL NETWORKS PREDICTIVE CONTROL METHOD FOR AFC-AGC SYSTEM

提出了一种板形板厚综合控制系统模型,给出了基于TH神经网络的增量式模型算法控制设计方法及其收敛特性,对板形板厚综合系统进行了前馈解耦设计,针对某热连轧精轧区七机架机组使用给出的控制方法进行了计算机模拟,证实了算法的有效性。

In this paper, an Automatic Flatness Control (AFC) and Automatic Gauge Control (AGC) synthetic system model is presented, a TH neural networks predictive design method for the forward decoupling synthetic system is given, the convergence of the neural networks is proofed. The computer simulation samples demonstrate the effectiveness of the method proposed.