RBF神经网络在薄膜厚度控制系统中的应用  

Application of RBF Neural Network in Film Thickness Control System

作　　者：李杨帆[1] 蒋品群[1] 罗晓曙[1] 李廷会[1] 隆媛媛[1] 

机构地区：[1]广西师范大学电子工程学院,广西桂林541004

出　　处：《现代电子技术》2010年第5期147-150,共4页Modern Electronics Technique

基　　金：广西教育厅科研项目(200608MS133)

摘　　要：针对双向拉伸薄膜厚度控制系统中,经典的PID控制器难以达到理想控制效果的问题,设计一个基于RBF神经网络整定的PID控制器。该控制器由RBF网络对系统进行在线辨识,找到最佳控制参数,并将其反馈给PID控制器,从而实现控制器参数的在线调整。仿真结果表明,本控制器具有超调量小,响应速度快和自适应性强等优点,可有效提高双向拉伸薄膜厚度控制系统的性能。Since it can＇t acquire satisfied control result by using traditional PID controller in biaxial oriented polypropylene film thickness control system,a PID controller based on RBF neural network is proposed. The RBF neural network is set up on-line reference model and offering gradient information for the PID controller,and on- line adjustment of the controller＇s parameters can be accomplished. The simulating result indicates that the control system is of small overshoot, rapid response and has good self - adaptability, which can improve the control performance of biaxial oriented polypropylene film thickness control system.

关 键 词：薄膜厚度控制 RBF神经网络 PID控制 超调 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]