Abstract: Abstract: Aiming at the problem of prescribed performance tracking control for uncertain strict-feedback nonlinear systems, this paper proposes a neural network tracking control method based on the fully-actuated system framework and improved prescribed perfo- rmance. The original system is converted into a high-order fully-actuated model through equivalent transformation, which significantly simplifies the controller structure and reduces the computational burden. In this paper, an improved performance function and its corre- sponding error transformation scheme are further proposed, and the constraint boundaries are employed to ensure the desired performa- nce of the system in terms of both steady-state and transient responses; meanwhile, the RBF neural network is utilized to perform linear approximation on the unknown nonlinear functions in the system, thereby enhancing the robustness of the system under model uncerta- inty. Finally, the Lyapunov method is adopted to prove the stability of the controller, ensuring that all signals of the closed-loop system are uniformly ultimately bounded. Simulation results verify the effectiveness of the proposed theoretical method, and the tracking error satisfies the prescribed performance constraints within the specified time.

Key words: strictly feedback nonlinear system, fully actuated system, prescribed performance, neural network, tracking control

摘要： 摘 要: 针对不确定严格反馈非线性系统的预设性能跟踪控制问题，本文提出一种基于全驱系统框架与改进预设性能的神经网络跟踪控制方法。通过等价变换将原系统转换为高阶全驱动模型，显著简化控制器结构并降低计算负担。文中进一步提出了改进型性能函数及其对应的误差变换方案，通过约束边界来确保系统在稳态和瞬态响应方面的预期性能；同时，利用RBF神经网络对系统中未知非线性函数进行线性逼近，增强系统在模型不确定性下的鲁棒性。最后采用李雅普诺夫方法证明控制器的稳定性，确保闭环系统所有信号一致最终有界。仿真结果验证了所提理论方法的有效性，并且跟踪误差在指定时间内满足预设性能约束。

关键词: 严格反馈非线性系统, 全驱动系统, 预设性能, 神经网络, 跟踪控制