摘要
为解决一类带干扰的模型不确定倒立摆系统中存在的两类未知项——未知函数和外界干扰,采用了基于Lyapunov函数稳定性的神经网络控制方法设计控制器。控制器设计中利用扩展卡尔曼滤波(EKF)消除系统观测噪声,获取系统状态的估计值,进而利用径向基函数(RBF)神经网络良好的逼近性来近似设计的控制律中的未知项。最后在倒立摆系统中对设计的神经网络控制器进行了仿真研究,仿真结果表明所设计的控制器能有效抑制外界干扰,在精确控制倒立摆的同时可以保证控制系统的稳定性和快速性。
This work studies the problem of unknown functions and uncertain disturbance of a class of nonlinear inverted pendulum systems,the design of the adaptive neural network controller is based on the Lyapunov function stability.The extended Kalman filter(EKF) is used in the controller design to eliminate systematic observation noise,then to get the estimated value for the system state,and the radial basis function(RBF) neural network is used to approximate the unknown part of the control law.Finally,a nonlinear inverted pendulum simulation system is built up to assess the neural network controller,the results show that the designed controller can effectively suppress the interference,the control system can obtain high accuracy with stability and celerity.
出处
《电脑知识与技术》
2011年第2期849-851,855,共4页
Computer Knowledge and Technology
关键词
RBF神经网络
EKF
倒立摆
控制
RBF neural networks
EKF
inverted pendulum
adaptive control