基于代数算法的RBF神经网络解耦控制  

DECOUPLING CONTROL OF RBF NETWORK BASED ON ALGEBRA ALGORITHM

作　　者：隆媛媛[1] 蒋品群[1] 李廷会[1] 罗晓曙[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：《计算机应用与软件》2010年第9期131-133,共3页Computer Applications and Software

基　　金：广西教育厅科研项目(200608MS133)

摘　　要：提出一种基于代数算法的RBF(Radial Basis Function)神经网络自适应PID控制方法。该方法采用动态的径向基函数网络对非线性系统进行在线辨识被控对象,并将获得的灵敏度信息对PID控制参数自整定,实现了系统的解耦控制。仿真结果表明该设计方案具有控制精度高,实时性好,且具有很强的鲁棒性和自适应性。An adaptive PID control approach of Radial Basis Function （RBF） neural network based on algebra algorithm is presented. This method performs online identification of the controlled object on non-linear system by means of dynamic RBF network, and self-tunes the sensitivity information acquired upon PID control parameters, thus the decoupling control of the system is achieved. The result of simulation shows that this designing scheme possesses the advantages of high precision, quick response speed and is of great robustness and adaptability.

关 键 词：代数算法 RBF神经网络 PID控制 解耦控制 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]