Premium
Robust exponential stability for discrete‐time interval BAM neural networks with delays and Markovian jump parameters
Author(s) -
Qiu Jiqing,
Lu Kunfeng,
Shi Peng,
Mahmoud Magdi S.
Publication year - 2010
Publication title -
international journal of adaptive control and signal processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.73
H-Index - 66
eISSN - 1099-1115
pISSN - 0890-6327
DOI - 10.1002/acs.1171
Subject(s) - control theory (sociology) , discrete time and continuous time , mathematics , interval (graph theory) , exponential stability , linear matrix inequality , stability (learning theory) , lyapunov function , markov process , artificial neural network , upper and lower bounds , computer science , mathematical optimization , nonlinear system , mathematical analysis , statistics , physics , control (management) , combinatorics , artificial intelligence , quantum mechanics , machine learning
This paper investigates the problem of global robust exponential stability for discrete‐time interval BAM neural networks with mode‐dependent time delays and Markovian jump parameters, by utilizing the Lyapunov–Krasovskii functional combined with the linear matrix inequality (LMI) approach. A new Markov process as discrete‐time, discrete‐state Markov process is considered. An exponential stability performance analysis result is first established for error systems without ignoring any terms in the derivative of Lyapunov functional by considering the relationship between the time‐varying delay and its upper bound. The delay factor depends on the mode of operation. Three numerical examples are given to demonstrate the merits of the proposed method. Copyright © 2010 John Wiley & Sons, Ltd.