Journal of the Institute of Electronics Engineers of Korea CI (전자공학회논문지CI)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

A Study on the Stability of Neural Network Control Systems

신경망 제어 시스템의 안정도에 관한 연구

  • Kim, Eun-Tai (Dept. of Control and Instrumentation Engr Hankyog National University) ;
  • Lee Hee-Jin (Dept. of Control and Instrumentation Engr Hankyog National University) ;
  • Kim Seung-Woo (Dept. of Information and Technology Engr Soonchunhyang University) ;
  • Park Mi-Gnon (Dept. of Electronic Engr Yonsei University)
  • 김은태 (國立大學敎 制御計測工學科) ;
  • 이의진 (國立大學敎 制御計測工學科) ;
  • 김승우 (順天鄕大學敎 情報技術工學部) ;
  • 박민용 (延世大學敎 電子工學部)
  • Published : 2000.01.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, an analysis of the stability for a class of discrete-time neural network control systems is presentd. Based on Lyapunov's direct method, a sufficient stability condition for the neural network control systems is systematically derived and the modified back propagation algorithm which reflects the derived stability condition is suggested. The modified BP originates from the derived sufficient condition and guarantees the exponential stability of the resulting trained closed system. Finally, computer simulation is included to show an example where the derived stability condition and the BP modified bythe condition is used to train the control plant.

본 논문에서는 이산 시간 신경망 제어 시스템의 안정도에 대한 해석을 하도록 한다. 우선 리아프노프의 직접법을 이용하여 신경망제어기를 포함하고 있는 시스템의 안정조건을 체계적으로 유도하고 이 유도된 안정조건을 반영하여 수정된 역전파 알고리즘을 제안한다. 이 수정된 역전파 알고리즘은 유도된 신경망 제어기 시스템의 안정조건을 반영한 학습 규칙이고 따라서 이를 이용하여 학습된 신경망 제어기의 경우 안정성을 보장하게 된다. 끝으로 컴퓨터 모의 실험에서는 제안한 신경망 제어 시스템의 안정조건과 이를 반영한 수정 역전파 알고리즘을 통하여 주어진 플랜트를 학습 제어하도록 한다.

Keywords

References

  1. J. Hopfield, 'Neural networks and physical systems with emergent collective computational abilities,' Proc. Nat. Acad. Sci. U.S., vol. 79, pp.2554-2558, 1982 https://doi.org/10.1073/pnas.79.8.2554
  2. T. Kohonen, Self-Organization and Associative Memory, New York: Springer-Verlag, 1984
  3. R. P. Lippmann, 'An introduction to computing with neural nets,' IEEE ASSP Mag., pp.4-22, 1987
  4. D. E. Rumelhart and J. L. McCelland, Parallel Distributed Processing, vol. 1. Cambridge, MA:M.I.T., 1986
  5. M. M. Gupta and D. H. Rao, Eds. Neuro-Control Systems: Theory and Applications. New York:IEEE, 1994
  6. W. T. Miller, R. S. Sutton and P. J. Werbos, Ed., Neural Networks for Control,. Cambridge, MA: MIT Press, 1990
  7. K. J. Hunt, D. Sbarbaro, R. Zbikowski and P. J. Gawthrop, 'Neural networks for control systems - A survey,' Automatica, vol. 28, no. 6, pp, 1083-1112, 1992. https://doi.org/10.1016/0005-1098(92)90053-I
  8. K. J. Hunt. G. W. Irwin and K. Warwick, Eds., Neural Network Engineering in Dynamic Control Systems, London: Springer Verlag, 1995
  9. G. Lightbody and G. W. Irwin, 'Nonlinear control structures based on embedded neural system models,' IEEE Trans. Neural Networks, vol. 8, no. 3, pp.553-567, 1997 https://doi.org/10.1109/72.572095
  10. H. Miyamoto, M. Kawato, T. Setoyama and R. Suzuki, 'Feedback error learning neural networks for trajectory control of a robotic manipulator,' Neural Networks, vol. 1, pp. 251-265, 1988 https://doi.org/10.1016/0893-6080(88)90030-5
  11. D. Nguyen and B. Widrow, 'The truck backer-upper: An example of self-learning in neural networks,' in Proc. IEEE Int. Joint Conf. Neural Networks, Washington, D.C., vol. 2, pp.11357-11363, 1989 https://doi.org/10.1109/IJCNN.1989.118723
  12. L. Behera, M. Gopal and S. Chaudhury, 'On adaptive trajectory tracking of a robot manipulator using inversion of its neural emulator,' IEEE Trans. Neural Networks, vol. 7, no. 6, pp. 1401-1414, 1996 https://doi.org/10.1109/72.548168
  13. R. M. Sanner and J. J. E. Slotine, 'Gaussian network for direct adaptive control,' IEEE Trans. Neural Networks, vol. 3, no. 6, pp. 837-863, 1992 https://doi.org/10.1109/72.165588
  14. K. S. Narendra, 'Adaptive of nonlinear multivariable systems using neural network,' Neural Networks, vol. 7, pp.737-752, 1994 https://doi.org/10.1016/0893-6080(94)90096-5
  15. R. Carelli, E. F. Camacho and D. Patino, 'A neural network based feedforward adaptive controller for robots,' IEEE Trans. Sys., Man, and Cyb., vol. 25, no. 9, pp. 1281-1288, 1995 https://doi.org/10.1109/21.400506
  16. E. P. Teixeira, E. B. Faria and A. Breunig, 'The use of feedforward neural networks to cancel nonlinearities of dynamic systems,' in Proc. IEEE Int. Joint Conf. Neural Networks, vol. 2, pp. 767-772, 1997 https://doi.org/10.1109/ICNN.1997.616119
  17. M. M. Polycarpou, 'Stable adaptive neural control scheme for nonlinear systems,' IEEE Trans. Automatic Control, vol. 41, no. 3, pp.447-451, 1996 https://doi.org/10.1109/9.486648
  18. K. Tanaka, 'An approach to stability criteria of neural-network control systems,' IEEE Trans. Neural Networks, vol. 7, no. 3, pp.629-642, 1996 https://doi.org/10.1109/72.501721
  19. D. B. Parker, 'Optimal algorithms for adaptive networks: Second-order backpropagation, second-order direction propagation and second-order Hebbian learning,' in Proc. IEEE Int. Joint Conf. Neural Networks, vol. 2, pp. 593-600, 1987
  20. Y. Iiguni, H. Sakai and H. Tokumaru, 'A real-time learning algorithm for a multilayered neural network based on the extended Kalman filter,' IEEE Trans. Signal Processing, vol. 40, no. 4, pp. 959-966, 1992 https://doi.org/10.1109/78.127966
  21. P. C. Y. Chen and J. K. Mills, 'Modeling of neural networks in feedback systems using describing functions,' in Proc. IEEE Int. Joint Conf. Neural Networks, vol. 2, pp. 773-738, 1997 https://doi.org/10.1109/ICNN.1997.616113
  22. M. E. Cotter, 'The Stone-Weierstrass theorem and its applications to neural nets,' IEEE Trans. Neural Networks, vol. 1, pp. 290-295, 1990 https://doi.org/10.1109/72.80265
  23. K. Funahashi, 'On the approximate realization of continuous mappings by neural networks,' Neural Networks, vol. 2, pp. 183-192, 1989 https://doi.org/10.1016/0893-6080(89)90003-8
  24. J. Villiers and E. Barnard, 'Backpropagation neural nets with one and two hidden layers,' IEEE Trans. Neural Networks, vol. 4, pp. 136-141, 1992 https://doi.org/10.1109/72.182704
  25. S. Kuntanapreeda and R. R. Fullmer, 'A training rule which guarantees finite-region stability for a class of closed-loop neural-network control systems,' IEEE Trans. Neural Networks, vol. 7, no. 3, pp. 745-752, 1996 https://doi.org/10.1109/72.501730
  26. C. T. Cheng, Linear system theory and design, 2nd ed., New York: Holt, Rinehart &Winston, 1970
  27. H. K. Khalil, Nonlinear Systems, Prentice-Hall, 1996
  28. D. Psaltis, A. Sideris, and A. A. Yamamura, 'A multilayered neural network controller,' IEEE Control System Mag., vol. 8, no. 2, pp. 17-21, 1988 https://doi.org/10.1109/37.1868