Passivity Analysis for Neuro Identifier with Different Time-Scales

  • Alejandro Cruz Sandoval
  • Wen Yu
  • Xiaoou Li
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4113)


Many physical systems contains fast and slow phenomenons. In this paper we propose a dynamic neural networks with different time-scales to model the nonlinear system. Passivity-based approach is used to derive stability conditions for neural identifer. Several stability properties, such as passivity, asymptotic stability, input-to-state stability and bounded input bounded output stability, are guaranteed in certain senses. Numerical examples are also given to demonstrate the effectiveness of the theoretical results.


Neural Network Asymptotic Stability Complete Convergence Gradient Descent Algorithm Global Exponential Stability 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Amari, S.: Competitive and Cooperative Aspects in Dynamics of Neural Excitation and Self-organization. Competition Cooperation Neural Networks 20, 1–28 (1982)Google Scholar
  2. 2.
    Grossberg, S.: Adaptive Pattern Classification and Universal Recording. Biol. Cybern. 23, 121–134 (1976)MATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Ioannou, P.A., Sun, J.: Robust Adaptive Control. Prentice-Hall, Englewood Cliffs (1996)MATHGoogle Scholar
  4. 4.
    Jagannathan, S., Lewis, F.L.: Identification of Nonlinear Dynamical Systems Using Multilayered Neural Networks. Automatica 32(12), 1707–1712 (1996)MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Jin, L., Gupta, M.: Stable Dynamic Dackpropagation Learning in Recurrent Neural Networks. IEEE Trans. Neural Networks 10, 1321–1334 (1999)CrossRefGoogle Scholar
  6. 6.
    Liu, H., Sun, F., Sun, Z.: Stability Analysis and Synthesis of Fuzzy Singularly Perturbed Systems. IEEE Transactions on Fuzzy Systems 13(2), 273–284 (2005)CrossRefGoogle Scholar
  7. 7.
    Lu, H., He, Z.: Global Exponential Stability of Delayed Competitive Neural Networks with Different Time Scales. Neural Networks 18(3), 243–250 (2005)MATHCrossRefGoogle Scholar
  8. 8.
    Meyer-Baese, A., Pilyugin, S.S., Chen, Y.: Global Exponential Stability of Competitive Neural Networks With Different Time Scales. IEEE Trans. on Neural Networks 14(3), 716–719 (2003)CrossRefGoogle Scholar
  9. 9.
    Ye, M., Zhang, Y.: Complete Convergence of Competitive Neural Networks with Different Time Scales. Neural Processing Letters 21(1), 53–60 (2005)CrossRefGoogle Scholar
  10. 10.
    Yu, W., Poznyak, A.S.: Indirect Adaptive Control via Parallel Dynamic Neural Networks. IEE Proceedings - Control Theory and Applications 146(1), 25–30 (1999)CrossRefGoogle Scholar
  11. 11.
    Yu, W., Li, X.: Some Stability Properties of Dynamic Neural Networks. IEEE Trans. Circuits and Systems, Part I 48(1), 256–259 (2001)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Alejandro Cruz Sandoval
    • 1
  • Wen Yu
    • 1
  • Xiaoou Li
    • 2
  1. 1.Departamento de Control AutomáticoCINVESTAV-IPNMéxico
  2. 2.Sección de Computación, Departamento de Ingeniería EléctricaCINVESTAV-IPNMéxico

Personalised recommendations