×

Switched exponential state estimation of neural networks based on passivity theory. (English) Zbl 1242.93036

Summary: In this paper, a new exponential state estimation method is proposed for switched Hopfield neural networks based on passivity theory. Through available output measurements, the main purpose is to estimate the neuron states such that the estimation error system is exponentially stable and passive from the control input to the output error. Based on augmented Lyapunov-Krasovskii functional, Jensen’s inequality, and Linear Matrix Inequalities (LMIs), a new delay-dependent state estimator for switched Hopfield neural networks can be achieved by solving LMIs, which can be easily facilitated by using some standard numerical packages. The unknown gain matrix is determined by solving delay-dependent LMIs. Finally, a numerical example is provided to demonstrate the effectiveness of the proposed method.

MSC:

93B35 Sensitivity (robustness)
93C15 Control/observation systems governed by ordinary differential equations
92B20 Neural networks for/in biological studies, artificial life and related topics

Software:

LMI toolbox
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Gupta, M.M., Jin, L., Homma, N.: Static and Dynamic Neural Networks. Wiley-Interscience, New York (2003)
[2] Hopfield, J.J.: Neurons with grade response have collective computational properties like those of a two-state neurons. Proc. Natl. Acad. Sci. USA 81, 3088–3092 (1984) · Zbl 1371.92015 · doi:10.1073/pnas.81.10.3088
[3] Farra, N.H., Mhaskar, P., Christofides, P.D.: Output feedback control of switched nonlinear systems using multiple Lyapunov functions. Syst. Control Lett. 54, 1163–1182 (2005) · Zbl 1129.93497 · doi:10.1016/j.sysconle.2005.04.005
[4] Liberzon, D.: Switching in Systems and Control: Foundations and Applications. Birkhäuser, Boston (2003) · Zbl 1036.93001
[5] Zong, G.D., Xu, S.Y., Wu, Y.Q.: Robust $\(\backslash\)mathcal{H}_{\(\backslash\)infty}$ stabilization for uncertain switched impulsive control systems with state delay: an LMI approach. Nonlinear Anal. Hybrid Syst 2, 1287–1300 (2008) · Zbl 1163.93386 · doi:10.1016/j.nahs.2008.09.018
[6] Hespanha, J.P., Morse, A.S.: Switching between stabilizing controllers. Automatica 38, 1905–1917 (2002) · Zbl 1011.93533 · doi:10.1016/S0005-1098(02)00139-5
[7] Niamsup, P.: Stability of time-varying switched systems with time-varying delay. Nonlinear Anal. Hybrid Syst 3, 631–639 (2009) · Zbl 1190.34094 · doi:10.1016/j.nahs.2009.05.006
[8] Zhang, Y., Liu, X.Z., Shen, X.M.: Stability of switched systems with time delay. Nonlinear Anal. Hybrid Syst 1, 44–58 (2007) · Zbl 1126.94021 · doi:10.1016/j.nahs.2006.03.001
[9] Tsividis, Y.: Switched neural networks. United States Patent, Patent number 4873661 (1989)
[10] Brown, T.X.: Neural networks for switching. IEEE Commun. Mag. 27, 72–81 (1989) · doi:10.1109/35.41403
[11] Muselli, M.: Gene selection through switched neural networks. In: Network Tools and Applications in Biology Workshop, pp. 27–28 (2003)
[12] Huang, H., Qu, Y., Li, H.: Robust stability analysis of switched Hopfield neural networks with time-varying delay under uncertainty. Phys. Lett. A 345, 345–354 (2005) · Zbl 1345.92013 · doi:10.1016/j.physleta.2005.07.042
[13] Lou, X.Y., Cui, B.T.: Delay-dependent criteria for robust stability of uncertain switched Hopfield neural networks. Int. J. Autom. Comput. 4, 304–314 (2007) · doi:10.1007/s11633-007-0304-0
[14] Ahn, C.K.: An $\(\backslash\)mathcal{H}_{\(\backslash\)infty}$ approach to stability analysis of switched Hopfield neural networks with time-delay. Nonlinear Dyn. 60, 703–711 (2010) · Zbl 1194.92005 · doi:10.1007/s11071-009-9625-6
[15] Jin, L., Nikiforuk, P.N., Gupta, M.M.: Adaptive control of discrete time nonlinear systems using recurrent neural networks. IEE Proc., Control Theory Appl. 141, 169–176 (1994) · Zbl 0803.93026 · doi:10.1049/ip-cta:19949976
[16] Wang, Z., Ho, D.W.C., Liu, X.: State estimation for delayed neural networks. IEEE Trans. Neural Netw. 16, 279–284 (2005) · doi:10.1109/TNN.2004.841813
[17] He, Y., Wang, Q.G., Wu, M., Lin, C.: Delay-dependent state estimation for delayed neural networks. IEEE Trans. Neural Netw. 17, 1077–1081 (2006) · doi:10.1109/TNN.2006.875969
[18] Liu, Y., Wang, Z., Liu, X.: Design of exponential state estimators for neural networks with mixed time delays. Phys. Lett. A 364, 401–412 (2007) · Zbl 05839158 · doi:10.1016/j.physleta.2006.12.018
[19] Wang, Z., Liu, Y., Liu, X.: State estimation for jumping recurrent neural networks with discrete and distributed delays. Neural Netw. 22, 41–48 (2009) · Zbl 1335.93125 · doi:10.1016/j.neunet.2008.09.015
[20] Balasubramaniam, P., Lakshmanan, S., Theesar, S.J.S.: State estimation for markovian jumping recurrent neural networks with interval timevarying delays. Nonlinear Dyn. 60, 661–675 (2010) · Zbl 1194.62109 · doi:10.1007/s11071-009-9623-8
[21] Willems, J.C.: Dissipative dynamical systems, part I: General theory. Arch. Ration. Mech. Anal. 45, 321–351 (1972) · Zbl 0252.93002 · doi:10.1007/BF00276493
[22] Byrnes, C.I., Isidori, A., Willem, J.C.: Passivity, feedback equivalence, and the global stabilization of minimum phase nonlinear system. IEEE Trans. Autom. Control 36, 1228–1240 (1991) · Zbl 0758.93007 · doi:10.1109/9.100932
[23] Boyd, S., Ghaoui, L.E., Feron, E., Balakrishinan, V.: Linear Matrix Inequalities in Systems and Control Theory. SIAM, Philadelphia (1994)
[24] Noldus, E.: Stabilization of a class of distributional convolutional equations. Int. J. Control 41, 947–960 (1985) · Zbl 0566.93048 · doi:10.1080/0020718508961174
[25] Gahinet, P., Nemirovski, A., Laub, A.J., Chilali, M.: LMI Control Toolbox. The Mathworks Inc., Natick (1995)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.