引用本文:刘春梅，沈毅，胡恒章.基于高阶神经网络扩展卡尔曼滤波器逆算法的非线性挠性结构的姿态控制[J].控制理论与应用,1999,16(4):511~514.[点击复制]
Liu Chunmei, Shen Yi and Hu Hengzhang.Attitude Control of Nonlinear Flexible Structure Based on Inversion Algorithm of Extended Kalman Filter of High-Order Neural Networks[J].Control Theory and Technology,1999,16(4):511~514.[点击复制]
基于高阶神经网络扩展卡尔曼滤波器逆算法的非线性挠性结构的姿态控制
Attitude Control of Nonlinear Flexible Structure Based on Inversion Algorithm of Extended Kalman Filter of High-Order Neural Networks
摘要点击 896  全文点击 438  投稿时间：1998-01-14  修订日期：1998-09-08
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  
  1999,16(4):511-514
中文关键词  高阶神经网络  扩展卡尔曼滤波器逆算法  非线性挠性结构  建模误差补偿
英文关键词  high-order neural networks  extended kalman filter  nonlinear flexible structure  compensation of modeling error
基金项目  
作者单位
刘春梅，沈毅，胡恒章  
中文摘要
      本文针对非线性挠性结构的姿态控制，提出了一种高阶神经网络及径向基函数网络（RBFN）相结合的网络模型，用于非线性挠性结构的动态系统辨识，以及基于卡尔曼滤波器（EKF）逆算法的控制策略。针对神经网络辨识时的模型误差，提出了一种简单有效的补偿方法，给出了建模误差补偿与未补偿时的仿真结果。仿真结果得出，该方法具有收敛快，算法简单，并能有效消除建模误差等优点。
英文摘要
      According to the attitude control of nonlinear flexible structure,a high-order（RBF） neural networks is presented in this paper which combines a high-order neural network and Radial basis function network (RBFN). The high-order RBFN is used for dynamical identification of nonlinear flexible structure and the design of control scheme based on inverse algorithm of extended Kalman filter (EKF).The modeling error can be compensated by a simple but effcient method that avoids the occurrence of divergence in the inverse algorithm,and the comparison of results is presented between modeling error compensation and no modeling error comparison.According to the simulation,it is explicit that this method is of these characters such as fast convergence and simple algorithm.