2025年01期 v.46 20-28+35页
罗振发
（广东工业大学，广东 广州510006）
摘要：针对状态不可测和存在外部未知扰动的非线性多智能体系统的一致跟踪问题，提出一种基于神经网络的分布式自适应脉冲控制方案。首先，构建复合扰动观测器，解决系统状态不可测与外部未知扰动耦合作用下的系统状态感知问题；然后，通过自适应脉冲更新律，实现神经网络权值参数的快速估计，提升系统的瞬态性能；接着，结合脉冲动态系统的Lyapunov稳定性理论，证明了闭环系统的一致最终有界性；最后，通过多单臂机械手系统的仿真实验，验证了该方案的有效性及优越性。
关键词：非线性多智能体；径向基函数神经网络；自适应控制；脉冲控制；观测器
中图分类号：TP13; TP183; O231.2 文献标志码：A 文章编号：1674-2605(2025)01-0003-10
DOI：10.3969/j.issn.1674-2605.2025.01.003 开放获取
Adaptive Pulse Control of Nonlinear Multi-agent Systems Based on Neural Networks
LUO Zhenfa
(Guangdong University of Technology, Guangzhou 510006, China)
Abstract: A distributed adaptive pulse control scheme based on neural networks is proposed for the consistent tracking problem of nonlinear multi-agent systems with unmeasurable states and external unknown disturbances. Firstly, construct a composite disturbance observer to solve the problem of system state awareness under the coupling of unmeasurable system states and external unknown disturbances. Then, by using an adaptive pulse update law, the neural network weight parameters can be quickly estimated to improve the transient performance of the system. Furthermore, based on the Lyapunov stability theory of pulse dynamic systems, it is proved that all signals in the closed-loop system are uniformly ultimately bounded. Finally, the effectiveness and superiority of the proposed scheme were verified through simulation experiments of a multi arm robotic arm system.
Keywords: nonlinear multi-agent system; radial basis function neural network; adaptive control; pulse control; observer
