In this article, an adaptive neural-network (NN) command-filtered output-feedback control strategy is proposed for a class of stochastic nonlinear systems (SNSs) with the actuator constraint. The problem of “explosion of complexity” existing in the conventional backstepping design procedure for SNSs is successfully resolved based on the command filter technique, and the error compensation mechanism is introduced to remove effectively the influence of filtered error. By using the NNs to identify the unknown nonlinear functions, a neural-network-based state observer is designed to estimate the unmeasurable states of the SNSs. Based on the quartic Lyapunov function, the stability of stochastic closed-loop systems is analyzed. It is proved that all signals of the closed-loop systems are bounded in probability, and the tracking error approaches a small neighborhood of the origin in probability. Finally, the effectiveness of the developed control algorithm in this article is verified by a comparison example.

中文翻译：

---

具有输入约束的随机非线性系统的命令过滤神经自适应输出反馈控制


在本文中，针对一类具有执行器约束的随机非线性系统（SNS）提出了一种自适应神经网络（NN）命令过滤输出反馈控制策略。基于命令过滤技术，成功解决了传统SNS反步设计过程中存在的“复杂性爆炸”问题，并引入误差补偿机制，有效消除过滤误差的影响。通过使用神经网络识别未知的非线性函数，设计了基于神经网络的状态观测器来估计 SNS 的不可测量状态。基于四次Lyapunov函数，分析了随机闭环系统的稳定性。证明了闭环系统的所有信号在概率上都是有界的，并且跟踪误差在概率上接近原点的一个小邻域。最后通过对比算例验证了本文所开发控制算法的有效性。