搜索

x
中国物理学会期刊

基于径向小波神经网络的混沌系统鲁棒自适应反演控制

CSTR: 32037.14.aps.61.030503

Robust adaptive radial wavelet neural network control for chaotic systems using backstepping design

CSTR: 32037.14.aps.61.030503
PDF
导出引用
  • 设计了一种具有自适应性和鲁棒性的反演控制律, 实现了对含有系统不确定性的类Rossler系统的控制. 首先通过小波神经网络辨识系统的非线性部分, 将系统转化为含有结构不确定性和参数不确定性的参数化模型; 然后, 对于系统中的参数不确定性, 设计自适应控制律, 在线估计未知参数; 对于系统中的结构不确定性, 设计鲁棒控制律, 使得系统具有鲁棒性. 最后, 通过仿真实现, 验证了以上控制方法的有效性.

     

    This paper designs an adaptive and robustness backstepping control law to realize the control of Rossler-like systems of uncertainties. First, a wavelet network is used for the identification the nonlinear part of the system to change it into parametric model with parametric and structural uncertainties; Then, for the parameter uncertainties, an adaptive control law is designed to online estimate the unknown parameters; for the structural uncertainties, a robust control law is designed to make the system robustness. Finally, The effective of this methodology is illustrated by the simulation results.

     

    目录

    /

    返回文章
    返回