Robust stabilising controller synthesis for discrete-time recurrent neural networks via state feedback
Robust stabilising controller synthesis for discrete-time recurrent neural networks via state feedback
复制标题
通过状态反馈的离散时间循环神经网络的鲁棒稳定控制器综合
DOI：
10.1504/ijmic.2010.035277
复制
发表时间：
2010-09
期刊：
影响因子：
--
通讯作者：
Zhang, Jianhai
中科院分区：
文献类型：
--
作者：
Dai, Guojun;Zhang, Senlin;Liu, Meiqin;Zhang, Huaixiang;Zhang, Jianhai
本文研究了含有范数有界不确定性的离散时间递归神经网络的镇定问题。一种新的神经网络模型，命名为标准神经网络模型（SNNM），是用来提供一个通用的框架，鲁棒镇定控制器的RNN综合。大多数现有的RNN都可以转换为SNNM，以统一的方式进行综合。应用李雅普诺夫稳定性理论和S-过程技术，设计状态反馈控制器，保证闭环动态离散系统的全局渐近稳定。控制器增益通过求解一组线性矩阵不等式得到。最后通过实例说明了该方法的有效性.
This paper addresses the stabilisation problem of discrete-time recurrent neural networks (RNNs) containing norm-bounded uncertainties. A novel neural network model, named standard neural network model (SNNM), is used to provide a general framework for robust stabilising controller synthesis of RNNs. Most of the existing RNNs can be transformed into SNNM to be synthesised in a unified way. Applying the Lyapunov stability theory and the S-procedure technique, state feedback controllers are designed to guarantee the global asymptotical stability of closed-loop dynamic discrete-time systems. The controller gains are obtained by solving a set of linear matrix inequalities. Examples are given to illustrate the transformation procedure and the effectiveness of the proposed design technique.