Adaptive Neural Control of Uncertain Nonstrict-Feedback Stochastic Nonlinear Systems with Output Constraint and Unknown Dead Zone
针对存在输出约束和未知死区的不确定非严格反馈随机非线性系统，提出一种基于神经网络的自适应控制器，利用障碍李雅普诺夫函数保证输出轨迹在预定范围内，并通过调节设计参数使跟踪误差收敛到原点附近小邻域。
An approximation-based adaptive neural controller is constructed for uncertain stochastic nonlinear systems in nonstrict-feedback form appearing dead-zone and output constraint. Neural networks (NNs) are directly utilized to approximate the unknown nonlinear functions existing in systems. A barrier Lyapunov function is introduced to ensure that the trajectory of output is limited within a predetermined range. By integrating NNs into the backstepping technique, an adaptive neural controller is designed to guarantee all variables existing in the considered closed-loop system are semi-globally uniformly ultimately bounded, and by appropriately tuning several design parameters online, the tracking error can be converged to a small neighborhood of the origin. Simulations on a numerical example are given to demonstrate the effectiveness of the method proposed in this paper.