针对带执行器饱和的多关节刚性机械臂系统,提出一种基于RBF神经网络补偿的输出反馈动态面控制.通过观测器实现角速度的观测,采用RBF网络实现执行器饱和的补偿;通过Lyapunov方法证明闭环系统的稳定性,实现高精度的角度和角速度跟踪.仿真结果表明,所提出的方法能够有效补偿系统存在的执行器饱和,显著减小跟踪误差,并且对于外界干扰具有一定的鲁棒性. Aiming at the multi-joint rigid manipulator system with actuator saturation, an output feedback dynamic surface control based on RBF neural network compensation is proposed. The observer is used to observe the angular velocity and the RBF network is used to compensate the actuator saturation. The Lyapunov method is used to prove The stability of the closed-loop system, and the realization of high-precision angular and angular velocity tracking.The simulation results show that the proposed method can effectively compensate the actuator saturation existing in the system, significantly reduce the tracking error and have a certain robustness to external disturbances.