一类欠驱动系统的自适应神经滑模控制

Adaptive neural network sliding mode control of a class of underactuated system

针对一类欠驱动系统在系统不确定性和外界干扰条件下的稳定控制问题,文章提出了自适应神经网络滑模控制策略。利用基于径向基函数(RBF)的神经网络在线估计系统的不确定量,采用李雅普诺夫方法设计自适应算法在线调整神经网络的参数;同时,利用带自适应算法的神经网络调节滑模控制的增益来消除滑模控制中的输入抖振现象;并通过李雅普诺夫定理论证了系统的稳定性。与传统滑模控制策略的仿真结果对比证明了系统是全局渐进稳定的,且控制器具有很好的适应性和鲁棒性。

An adaptive neural network sliding mode control strategy is proposed to realize the stable control of a class of underactuated system in presence of uncertain parameters of system and external disturbances. The parameters of neural network can be adjusted online by using Lyapunov method through radial basis function（RBF） neural network control. Moreover, the gain of sliding mode con- trol is adjusted by using dual RBF neural network control with adaptive adjustment algorithm, so as to eliminate the chattering phenomenon in sliding mode control. The stability and tracking perform- ance of the system are verified by Lyapunov theory. Finally, the results of simulation examples and the comparison with traditional sliding mode control confirm the global asymptotic stability of the sys- tem and the effectiveness and robustness of the proposed controller.