Research Papers

Further Results on Exponential Robust Stability Analysis for Recurrent Neural Networks With Time-Varying Delay

[+] Author and Article Information
Pin-Lin Liu

Department of Automation Engineering,
Institute of Mechatronoptic System,
Chienkuo Technology University,
Changhua, 500, Taiwan, China
e-mail: lpl@cc.ctu.edu.tw

Contributed by the Dynamic Systems Division of ASME for publication in the JOURNAL OF DYNAMIC SYSTEMS, MEASUREMENT, AND CONTROL. Manuscript received March 26, 2013; final manuscript received November 6, 2014; published online January 9, 2015. Assoc. Editor: YangQuan Chen.

J. Dyn. Sys., Meas., Control 137(4), 041018 (Apr 01, 2015) (8 pages) Paper No: DS-13-1136; doi: 10.1115/1.4029060 History: Received March 26, 2013; Revised November 06, 2014; Online January 09, 2015

In this paper, the problems of determining the robust exponential stability and estimating the exponential convergence rate for recurrent neural networks (RNNs) with parametric uncertainties and time-varying delay are studied. The relationship among the time-varying delay, its upper bound, and their difference is taken into account. The developed stability conditions are in terms of linear matrix inequalities (LMIs) and the integral inequality approach (IIA), which can be checked easily by recently developed algorithms solving LMIs. Furthermore, the proposed stability conditions are less conservative than some recently known ones in the literature, and this has been demonstrated via four examples with simulation.

Copyright © 2015 by ASME
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Fig. 1

The simulation of the example 3 for h = 7.84 s




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In