© The Institution of Engineering and Technology
In this study, the authors investigate the problem of global exponential stability of static neural networks with time delay and impulses. Three types of impulses are studied: the impulses are input disturbances; the impulses are ‘neutral’ type, that is, they are neither helpful for stability of neural networks nor destabilising; and the impulses are stabilising. For each type of impulses, by using Lyapunov function and Razumikhintype techniques, sufficient conditions for global exponential stability are established in terms of linear matrix inequalities with respect to suitable classes of impulse time sequences. The new sufficient conditions can explicitly reveal the effects of time delay, impulses etc., on the stability. Numerical results are given to show the less conservatism of the obtained criteria compared with the existing ones.
References


1)

C.M. Marcus ,
R.M. Westervelt
.
Stability of analog neural networks with delay.
Phys. Rev. A
,
1 ,
347 
359

2)

Q. Liu ,
J. Cao ,
Y. Xia
.
A delayed neural network for solving linear projection equations and its analysis.
IEEE Trans. Neural Netw.
,
4 ,
834 
843

3)

Tian, J.Y., Liu, J.Q.: `Apnea detection based on time delay neural network', Proc. 2005 IEEE Engineering in Medicine and Biology 27th Annual Conf., 2005, Shanghai, China, p. 2571–2574.

4)

Juang, J.G., Chang, H.H.: `Application of time delay neural network to automatic landing control', Proc. 2002 IEEE Int. Conf. on Control Applications, 2002, p. 151–155.

5)

F. Lavagetto
.
Timedelay neural network for estimating lip movements from speech analysis: a useful tool in audiovideo synchronization.
IEEE Trans. Circuits Syst. Video Technol.
,
5 ,
786 
800

6)

Ran, W.L., Qiao, J.F., Ye, X.D.: `Softmeasuring approach to online predict BOD based on PCA timedelay neural network', Proc. Fifth World Congress on Intelligent Control and Automation, 2004, Hangzhou, China, p. 3483–3487.

7)

S. Arik
.
Global asymptotic stability of a large class of neural networks with constant time delays.
Phys. Lett. A
,
6 ,
504 
511

8)

J. Cao
.
Periodic oscillation and exponential stability of delayed CNNs.
Phys. Lett. A
,
157 
163

9)

J. Cao ,
D. Zhou
.
Stability analysis of delayed cellular neural networks.
Neural Netw.
,
9 ,
1601 
1605

10)

W.H. Chen ,
Z.H. Guan ,
X. Lu
.
Delaydependent exponential stability of neural networks with variable delays.
Phys. Lett. A
,
355 
363

11)

W.H. Chen ,
X. Lu
.
New delaydependent exponential stability criteria for neural networks with variable delays.
Phys. Lett. A
,
53 
58

12)

K. Gopalsamy ,
X.Z. He
.
Delay independent stability in bidirectional associative memory neural networks.
IEEE Trans. Neural Netw.
,
6 ,
998 
1002

13)

H.D. Qi ,
L. Qi
.
Deriving sufficient conditions for global asymptotic stability of delayed neural networks via nonsmooth analysis.
IEEE Trans. Neural Netw.
,
1 ,
99 
109

14)

H. Ye ,
N. Micheal ,
K. Wang
.
Robust stability of nonlinear timedelay systems with applications to neural networks.
IEEE Trans. Circuits Syst. I, Fundam. Theory Appl.
,
7 ,
532 
543

15)

Q. Zhang ,
X. Wei ,
J. Xu
.
Global exponential convergence analysis of delayed neural networks with time varying delays.
Phys. Lett. A
,
6 ,
537 
544

16)

H. Qiao ,
J. Peng ,
Z.B. Zu ,
B. Zhang
.
A reference model approach to stability analysis of neural network.
IEEE Trans. Syst., Man, Cybern. B, Cybern.
,
6 ,
925 
936

17)

Z.B. Xu ,
H. Qiao ,
J. Peng ,
B. Zhang
.
A comparative study on two modeling approaches in neural networks.
Neural Netw.
,
1 ,
73 
85

18)

P. Li ,
J. Cao
.
Stability in static delayed neural networks: a nonlinear measure approach.
Neurocomputing
,
1776 
1781

19)

J. Liang ,
J. Cao
.
A basedon LMI stability criterion for delayed recurrent neural networks.
Chaos Solitons Fractals
,
1 ,
154 
160

20)

H. Shao
.
Delaydependent approaches to globally exponential stability for recurrent neural networks.
IEEE Trans. Circuits Syst. II, Exp. Briefs
,
6 ,
591 
595

21)

C.D. Zheng ,
H. Zhang ,
Z. Wang
.
Delaydependent globally exponential stability criteria for static neural networks: an LMI approach.
IEEE Trans. Circuits Syst. II, Exp. Briefs
,
7 ,
605 
609

22)

C.Y. Lu ,
T.J. Su ,
S.C. Huang
.
Delaydependent stability analysis for recurrent neural networks with timevarying delay.
IET Control Theory Appl.
,
8 ,
736 
742

23)

D.D. Bainov ,
P.S. Simeonov
.
(1989)
Systems with impulse effect: stability, theory and applications.

24)

V. Lakshmikantham ,
D.D. Bainov ,
P.S. Simeonov
.
(1989)
Theory of impulsive differential equations.

25)

W.H. Chen ,
W.X. Zheng
.
Global exponential stability of impulsive neural networks with variable delay: an LMI approach.
IEEE Trans. Circuits Syst. I, Regul. Papers
,
6 ,
1248 
1259

26)

S. Long ,
D. Xu
.
Delaydependent stability analysis for impulsive neural networks with time varying delays.
Neurocomputing
,
1705 
1713

27)

Y. Xia ,
J. Cao ,
S.S. Cheng
.
Global exponential stability of delayed cellular neural networks with impulses.
Neurocomputing
,
2495 
2501

28)

Z. Yang ,
D. Xu
.
Stability analysis of delay neural networks with impulsive effects.
IEEE Trans. Circuits Syst. II, Anal. Digit. Signal Process.
,
8 ,
517 
521

29)

Y. Zhang ,
J. Sun
.
Stability of impulsive neural networks with time delays.
Phys. Lett. A
,
44 
50

30)

Zhao, Y.C., Wang, L.S.: `Global exponential stability of impulsive static neural networks with timevarying delays', Fourth Int. Conf. on Computer Sciences and Convergence Information Technology, 2009, Seoul, Korea, p. 1236–1239.

31)

A. Berman ,
R.J. Plemmons
.
(1979)
Nonnegative matrices in mathematical sciences.

32)

S. Boyd ,
L. El Ghaoui ,
E. Feron ,
V. Balakrishnan
.
(1994)
Linear matrix inequalities in systems and control theory.

33)

Guo, X., Li, Q., Chen, Y.: `Global exponential stability analysis for recurrent neural networks with timevarying delay', Control and Decision Conf., 2009, Guilin, China, p. 2976–2980.

34)

H. Shao
.
Novel delaydependent stability results for neural networks with timevarying delays.
Circuits Syst. Signal Process.
,
4 ,
637 
647

35)

H. Shao
.
Less conservative delaydependent stability criteria for neural networks with timevarying delays.
Neurocomputing
,
1528 
1532

36)

Y.Y. Wu ,
Y.Q. Wu
.
Stability analysis for recurrent neural networks with timevarying delay.
Int. J. Autom. Comput.
,
3 ,
223 
227
http://iet.metastore.ingenta.com/content/journals/10.1049/ietcta.2010.0329
Related content
content/journals/10.1049/ietcta.2010.0329
pub_keyword,iet_inspecKeyword,pub_concept
6
6