基于积分并行学习的不确定非线性系统的自适应神经网络控制
首发时间:2024-03-15
摘要:本文研究了一类不确定严格反馈非线性系统的自适应神经网络控制问题. 结合积分并行学习(integral concurrent learning, ICL)与反步技术, 提出了一种新颖的自适应神经网络控制算法. 该方法采用径向基神经网络(radial basis function neural networks, RBFNNs)逼近系统的未知动态. 同时, 基于历史存储数据和当前数据, 利用ICL技术对神经网络权重进行更新. 该控制算法的显著特点是在无需满足持续激励(persistent excitation,PE)条件下, 可实现对闭环系统未知动态的准确识别/学习. 最后, 通过仿真算例验证了该控制算法的有效性.
关键词: 积分并行学习, 神经网络控制, 持续激励
For information in English, please click here
Adaptive Neural Network Control For Uncertain Nonlinear Systems Using Integral Concurrent Learning
Abstract:This paper studies the issue of adaptive neural network control for a class of uncertain strict-feedback nonlinear systems. A novel adaptive neural network control algorithm is proposed by combining integral concurrent learning (ICL) with backstepping techniques. The approach employs radial basis function neural networks (RBFNNs) to approximate the unknown dynamics of the system. Concurrently, the neural network weights are updated using ICL based on historical stored data and current data. The significant feature of this control algorithm is its ability to accurately identify/learn the unknown dynamics of the closed-loop system without requiring persistent excitation (PE) conditions. Finally, the effectiveness of the proposed control algorithm is confirmed through simulation examples.
Keywords: Integral concurrent learning, neural network control, persistent excitation
引用
No.****
动态公开评议
共计0人参与
勘误表
基于积分并行学习的不确定非线性系统的自适应神经网络控制
评论
全部评论