Skip to main navigation Skip to search Skip to main content

Finite-time boundedness of uncertain switched time-delay neural networks with mode-dependent average dwell time

  • Shun Wang*
  • , Chao Ma
  • , Ming Zeng
  • , Zhiwei Yu
  • , Yuanhong Liu
  • *Corresponding author for this work
  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper investigates the finite-time boundedness (FTB) problems for a class of uncertain switched neural networks (NNs) consisting of both stable and unstable time-delay subsystems. A parameter-dependent running time description (PDRTD) approach is invoked to obtain the proposed FTB criteria. The switched NNs with only unstable subsystems are firstly derived under the mode-dependent average dwell time (MDADT) approach, which is more applicable than the average dwell time (ADT). Then the case is extended to the switched NNs with both stable and unstable subsystems. A numerical example is given to show the validity and potential of the developed techniques.

Original languageEnglish
Title of host publicationProceedings of the 33rd Chinese Control Conference, CCC 2014
EditorsShengyuan Xu, Qianchuan Zhao
PublisherIEEE Computer Society
Pages4078-4083
Number of pages6
ISBN (Electronic)9789881563842
DOIs
StatePublished - 11 Sep 2014
EventProceedings of the 33rd Chinese Control Conference, CCC 2014 - Nanjing, China
Duration: 28 Jul 201430 Jul 2014

Publication series

NameProceedings of the 33rd Chinese Control Conference, CCC 2014
ISSN (Print)1934-1768
ISSN (Electronic)2161-2927

Conference

ConferenceProceedings of the 33rd Chinese Control Conference, CCC 2014
Country/TerritoryChina
CityNanjing
Period28/07/1430/07/14

Keywords

  • Finite-Time Boundedness
  • Mode-Dependent Average Dwell Time
  • Stable and Unstable Subsystems
  • Switched Neural Networks
  • Time-Varying Delays

Fingerprint

Dive into the research topics of 'Finite-time boundedness of uncertain switched time-delay neural networks with mode-dependent average dwell time'. Together they form a unique fingerprint.

Cite this