中文摘要：

研究一类空间机械臂系统的基于模式的控制方法。首先在训练阶段,基于确定性学习理论设计自适应神经网络控制器使机械臂系统跟踪不同的任务模式,得到对应于不同任务模式的一系列空间机械臂闭环动态的局部准确神经网络建模,并利用这些模型构造对应不同任务模式的常值神经网络控制器。其次,在测试阶段,首先快速识别出任务模式,然后调用相应的常值神经网络控制器实现对空间机械臂系统基于模式的闭环控制。理论证明基于模式的控制方法可提高机械臂闭环系统的控制性能,并可避免频繁切换。理论结果最后在空间机械臂中得到了仿真校验。

英文摘要：

Stability issues for mode-based control of space manipulator systems are studied in this paper. The technique used is to employ a newly developed deterministic learning（ DL） theory,by defining a tracking control task as a reference mode,identification of which is achieved in a local region via DL. Likewise,identification of the local controlled manipulator system dynamics corresponding to each reference mode is also realized. Then a set of mode-based constant NN controllers are constructed accordingly by using the obtained manipulator system dynamics. When tracking control task begins to change,rapid recognition of reference mode is naturally implemented due to the internal matching for reference system dynamics,then the corresponding NN controller with learned experience is selected and activated. Research results show that the mode-based NN controllers can guarantee the stability of the mode-based space manipulator systems and improve the control performance. Finally,numerical simulations of space manipulator systems have demonstrated the effectiveness of the proposed approach.