基于RBF神经网络的流浆箱PID解耦控制  

PID Decoupling Control of Headbox Based on RBF Neural Network

作　　者：曹露[1] 胡慕伊[1] 

机构地区：[1]南京林业大学江苏省制浆造纸科学与技术重点实验室,江苏南京210037

出　　处：《造纸科学与技术》2011年第6期138-141,共4页Paper Science & Technology

基　　金：江苏省制浆造纸科学与技术重点实验室开放基金项目(200909)

摘　　要：针对气垫式流浆箱总压和浆位控制系统之间存在的耦合现象,设计了一种基于RBF网络辨识的流浆箱PID解耦控制。该方法采用RBF网络实时辨识流浆箱的数学模型,为PID控制器参数的调整提供Jacobian信息,最终实现对流浆箱的解耦控制。仿真结果表明,该解耦控制器能够有效地减小总压和浆位之间的耦合影响,并使得控制系统具有较好的静态和动态性能,适合气垫式流浆箱的控制。To solve the coupling problem between total pressure and liquid level in air-cushioned headbox control system, a PID decoupling controller based on the identifier of RBF neural network was put forward. To get the Jacobian information for the PID controller the headbox real-time model was identified by RBF network. Finally, the decoupling control of air-cushioned headbox was realized. The results of simulation show that the controller can effectively reduce the coupling influence between total pressure and liquid level, and improve the static and dynamic characteristics of the control system, thus it is suitable for the air-cushioned headbox control.

关 键 词：径向基神经网络 气垫式流浆箱 PID控制 解耦 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]