纸张多变量控制系统的分析与设计

摘要

针对纸张定量、水分和灰分系统的强耦合、时滞特点,运用基于对角递归神经网络的多变量自整定PID控制方法,实时调整PID控制器的参数,实现系统的解耦功能.实验仿真结果表明,该控制方法系统适应能力较强、响应速度快、抗干扰能力强.%Considering papermaking process has strong coupling and time-delay characteristics, a method of PID control by unpacking coupling based on the diagonal recurrent neural network is provided. It can perfectly achieve to decouple multi-variable control system by using diagonal recurrent neural network to identify the system model and adjust the PID parameters. The results indicate that the PID control by unpacking coupling has powerful adaptive ability, short response and fast anti-interference.