引用本文:刘妹琴,颜钢锋.递归多层感知器的稳定性分析——LMI方法[J].控制理论与应用,2003,20(6):897~902.[点击复制]
LIU Mei-qin,YAN Gang-feng.Stability analysis of recurrent multilayer perceptrons: LMI approach[J].Control Theory and Technology,2003,20(6):897~902.[点击复制]
递归多层感知器的稳定性分析——LMI方法
Stability analysis of recurrent multilayer perceptrons: LMI approach
摘要点击 2585  全文点击 1909  投稿时间：2001-09-07  修订日期：2003-04-28
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/j.issn.1000-8152.2003.6.017
  2003,20(6):897-902
中文关键词  标准神经网络模型  递归多层感知器  状态空间扩展法  线性矩阵不等式
英文关键词  standard neural network model (SNNM)  recurrent multilayer perceptron (RMLP)  state space extension method  linear matrix inequality (LMI)
基金项目  
作者单位E-mail
刘妹琴 浙江大学 电气工程学院 系统科学与工程学系, 浙江 杭州 310027 liumeiqin@cee.zju.edu.cn 
颜钢锋 浙江大学 电气工程学院 系统科学与工程学系, 浙江 杭州 310027 ygf@cee.zju.edu.cn 
中文摘要
      递归多层感知器(RMLP)在工程上应用比较多,但对其稳定性的研究还比较少.本文提出一种新的神经网络模型———标准神经网络模型(SNNM),通过状态空间扩展法,将RMLP转化为SNNM,而SNNM的稳定性分析可转化为一组线性矩阵不等式(LMI)的求解,利用Matlab/LMIToolbox求解LMI,从而判定RMLP的Lyapunov稳定性,并考虑非零阈值对稳定性的影响.该方法也适用于其他类型的递归神经网络(RNN)的稳定性分析.
英文摘要
       Recurrent multilayer perceptrons (RMLPs) were widely applied to the industrial processes, but stability analysis of RMLPs was seldom researched at present. A novel neural network model named as standard neural network model (SNNM) was advanced. By applying the state space extension method, RMLPs were converted to the SNNMs. Stability conditions of the SNNMs were transformed into some linear matrix inequalities (LMIs). LMIs were solved by Matlab/LMI Toolbox to determine whether RMLPs were Lyapunov stable or not. And the effect of nonzero biased in RMLPs on stability was taken into account. The proposed approach can also be applied to other forms of recurrent neural networks (RNNs).