An LMI approach for global robust dissipativity analysis of T–S fuzzy neural networks with interval time-varying delays

2012 ◽  
Vol 39 (3) ◽  
pp. 3345-3355 ◽  
Author(s):  
S. Muralisankar ◽  
N. Gopalakrishnan ◽  
P. Balasubramaniam
Keyword(s):  
Neural Networks ◽  
Fuzzy Neural Networks ◽  
Time Varying ◽  
Lmi Approach ◽  
Interval Time ◽  
Fuzzy Neural ◽  
Dissipativity Analysis

scholarly journals Dissipativity analysis of stochastic fuzzy neural networks with randomly occurring uncertainties using delay dividing approach

2019 ◽  
Vol 24 (4) ◽  
Author(s):  
Sundaram Senthilraj ◽  
Ramachandran Raja ◽  
Jinde Cao ◽  
Habib M. Fardoun
Keyword(s):  
Neural Networks ◽  
Sufficient Conditions ◽  
Lyapunov Stability Theory ◽  
Fuzzy Neural Networks ◽  
Linear Matrix ◽  
Time Varying ◽  
Randomly Occurring Uncertainties ◽  
Fuzzy Neural ◽  
Delay Partitioning ◽  
Dissipativity Analysis

This paper focuses on the problem of delay-dependent robust dissipativity analysis for a class of stochastic fuzzy neural networks with time-varying delay. The randomly occurring uncertainties under consideration are assumed to follow certain mutually uncorrelated Bernoulli-distributed white noise sequences. Based on the Itô's differential formula, Lyapunov stability theory, and linear matrix inequalities techniques, several novel sufficient conditions are derived using delay partitioning approach to ensure the dissipativity of neural networks with or without time-varying parametric uncertainties. It is shown, by comparing with existing approaches, that the delay-partitioning projection approach can largely reduce the conservatism of the stability results. Numerical examples are constructed to show the effectiveness of the theoretical results.

A DELAY-DEPENDENT APPROACH TO ROBUST PASSIVITY ANALYSIS FOR TAKAGI-SUGENO FUZZY UNCERTAIN RECURRENT NEURAL NETWORKS WITH MIXED INTERVAL TIME-VARYING DELAYS

2013 ◽  
Vol 21 (03) ◽  
pp. 415-433 ◽  
Author(s):  
K. H. TSENG ◽  
J. S. H. TSAI ◽  
C. Y. LU
Keyword(s):  
Neural Networks ◽  
Sufficient Conditions ◽  
Fuzzy Neural Networks ◽  
Linear Matrix ◽  
Uncertain Parameters ◽  
Time Varying ◽  
Interval Time ◽  
Passivity Analysis ◽  
Fuzzy Neural ◽  
Delay Dependent

This paper deals with the passivity analysis problem for Takagu-Sugeno (T-S) fuzzy neural networks with mixed interval time-varying delays and uncertain parameters. The time delays comprise discrete and distributed interval time-varying delays and the uncertain parameters are norm-bounded. Delay-dependent sufficient conditions for the passivity problem are obtained by using Lyapunov-Krasovskii functional approach and linear matrix inequality (LMI) technique. The important feature of the results lies in that it does not make use of upper bounds to introduce some degree of conservativeness. Two illustrative examples are exploited in order to illustrate the effectiveness of the proposed design procedures.

Type-II fuzzy neural networks with self-organizing recurrent intervals for dynamic time-varying system identification

2011 ◽  
Vol 19 (6) ◽  
pp. 1406-1413 ◽  
Author(s):  
李迪 LI Di ◽  
陈向坚 CHEN Xiang-jian ◽  
续志军 XU Zhi-jun ◽  
杨帆 YANG Fan ◽  
牛文达 NIU Wen-da
Keyword(s):  
Neural Networks ◽  
System Identification ◽  
Fuzzy Neural Networks ◽  
Time Varying ◽  
Type Ii ◽  
Fuzzy Neural ◽  
Dynamic Time ◽  
Self Organizing

Periodicity of Cohen–Grossberg-type fuzzy neural networks with impulses and time-varying delays

2019 ◽  
Vol 325 ◽  
pp. 254-259 ◽  
Author(s):  
Fangru Meng ◽  
Kelin Li ◽  
Qiankun Song ◽  
Yurong Liu ◽  
Fuad E. Alsaadi
Keyword(s):  
Neural Networks ◽  
Fuzzy Neural Networks ◽  
Time Varying ◽  
Fuzzy Neural
Sign in / Sign up

Export Citation Format

Share Document