摘要
基于逆动力学控制的思想,本文提出一种RBF神经网络逆控制与PD加前馈控制相结合的在线自学习的双模控制方案。构造一个动态伪线性对象,使非线性对象的控制问题转换为线性对象的控制问题。仿真实验证明了该方法不仅能使非线性系统具有良好的动态跟踪性能和抗干扰能力,而且具有较强的自适应性和鲁棒性。
A dual-mode control strategy based on inverse control concept was presented,which is based on the proposed radical basis function （RBF） neural network inverse controller and a parameters self-adaptive proportion differenced （PD） controller. The model of controller and the plant are in series,which forms a dynamic pseudo linear system. The dynamic pseudo linear plant can be controlled by PD control along with feed-forward control method. With the help of simulation,the control strategy can not only has the nice dynamic track performance and resistances to disturbance,but also possesses strong self-adaptability and excellent robustness.
出处
《微计算机信息》
2009年第34期54-56,共3页
Control & Automation
基金
江苏省高校自然科学基础研究项目
基金申请人:孙红兵
项目名称:多主体及移动主体智能协作技术在大型智能结构健康监测中的应用
颁发部门:江苏省教育厅(08kjd560009)
关键词
双模控制
开关切换
RBF辨识
伪线性对象
前馈
dual-mode control
switching
RBF identifier
feed-forward
dynamic pseudo linear plant
