(Design of Neural Network Controller for Contiunous-Time Chaotic Nonlinear Systems)

연속 시간 혼돈 비선형 시스템을 위한 신경 회로망 제어기의 설계

  • Published : 2002.01.01

Abstract

This paper presents a design method of the neural network-based controller using an indirect adaptive control method to deal with an intelligent control for chaotic nonlinear systems. The proposed control method includes the identification and control Process for chaotic nonlinear systems. The identification process for chaotic nonlinear systems is an off-line process which utilizes the serial-parallel structure of multilayer neural networks and simple state space neural networks. The control process is an on-line process which uses the trained neural networks as the system model. An error back-propagation method was used for training of identification and control for chaotic nonlinear systems. The performance of the proposed neural network controller was evaluated by application to the Duffing equation and the Lorenz equation, and the proposed controller was compared with other neural network-based controllers by computer simulations.

본 논문에서는 혼돈 비선형 시스템의 지능 제어를 위해 간접 적응 제어 방식에 기초한 신경 회로망 제어기 설계 방법을 제안하였다. 제안된 제어 방법은 혼돈 비선형 시스템의 동정을 위해 다층 신경 회로망과 간단한 상태 공간 신경 회로망을 사용한 직-병렬 동정 구조를 이용하여 오프 라인으로 동정 과정을 수행하였으며, 학습된 혼돈 비선형 시스템에 대한 신경 회로망 모델을 사용하여 온 라인으로 제어를 수행하였다. 이때 혼돈 비선형 시스템의 동정 및 제어를 위한 학습 방법은 오차 역전파 방법을 사용하였다. 한편 본 논문에서 제안된 제어 방법을 연속 시간 혼돈 비선형 시스템인 Duffing 방정식과 Lorenz 방정식에 각각 적용하여 신경 회로망을 사용한 기존의 제어 방법과 컴퓨터 모의 실험을 통해 제어 성능을 비교 및 고찰하였다.

Keywords

References

  1. G. Chen and X. Dong, 'From Chaos to Order-Perspectives and Methodologies in Controlling Chaos Nonlinear Dynamical Systems,' Int. J. Bifurcation and Chaos, Vol. 3, No. 6, pp. 1363-1409, 1993 https://doi.org/10.1142/S0218127493001112
  2. E. Ott, C. Grebogi, and J. A. Yorke, 'Controlling Chaos,' Phys. Rev. Lett., Vol. 64, No. 11, pp. 1196-1199, 1990 https://doi.org/10.1103/PhysRevLett.64.1196
  3. E. A. Jackson and A. W. Hubler, 'Preiodic Entrainment of Chaotic Logistic Map Dynamics,' Physica D, Vol. 44, pp. 407-420, 1990 https://doi.org/10.1016/0167-2789(90)90155-I
  4. G. Chen and X. Dong, 'On Feedback Control of Chaotic Continuous-Time Systems,' IEEE Trans. Circuits and Systems, Vol. 40, No. 9, pp. 591-601, 1993 https://doi.org/10.1109/81.244908
  5. G. Chen, 'Controlling Chua's Global Unifolding Circuit Family,' IEEE Trans. Circuits and Systems, Vol. 40, No. 7, pp. 829-832, 1993 https://doi.org/10.1109/81.251821
  6. G. Chen and X. Dong, 'On Feedback Control of Chaotic Nonlinear Dynamic Systems,' Int. J. Bifurcation and Chaos, Vol. 2, No. 2, pp. 407-411, 1992 https://doi.org/10.1142/S0218127492000392
  7. I. J. Leontaritis and S. A. Billings, 'Input-Output Parametric Models for Nonlinear Systems : Part I & II,' Int. J. Contr., Vol. 41, No. 2, pp. 303-353, 1952 https://doi.org/10.1080/0020718508961129
  8. I. J. Leontaritis and S. A. Billings, 'Input-Output Parametric Models for Nonlinear Systems : Part I & II,' Int. J. Contr., Vol. 41, No. 2, pp. 303-353, 1952 https://doi.org/10.1080/0020718508961130
  9. H. K. Qammer and F. Mossayebi, 'Systems Identification and Model-Based Control of a Chaotic System,' Int. J. Bifurcation and Chaos, Vol. 4, No. 4, pp. 843-851, 1994 https://doi.org/10.1142/S0218127494000605
  10. H. Nijmeijer and H. Berghuis, 'On Lyapunov Control of the Duffing Equation,' IEEE Trans. Circuits and Systems, Vol. 42, No. 8, pp. 473-477, 1995 https://doi.org/10.1109/81.404059
  11. G. Chen and X. Dong, 'Identification and Control of Chaotic Systems : An Artificial Neural Network Approach,' Proc. IEEE Int. Symposium on Circuits and Systems, Seattle, WA, pp. 1177-1182, 1995 https://doi.org/10.1109/ISCAS.1995.520354
  12. H. Wang, K. Tanaka, and T. Ikeda, 'Fuzzy Modelling and Control of Chaotic Systems,' IEEE Symposium on Circuit and System, pp. 209-212, 1996 https://doi.org/10.1109/ISCAS.1996.541517
  13. Ted W. Frison, 'Controlling Chaos with a Neural Network,' Proc. Int. Conf. on Neural Network, Baltimore, MD, pp. 75-80, 1992 https://doi.org/10.1109/IJCNN.1992.226981
  14. S. H. Strogatz, Nonlinear Dynamics and Chaos, Addison-Wesley, 1994
  15. D. Psaltis, A. Sideris, and A. A. Yamamura, 'A Multilayered Neural Network Controller', IEEE Control Systems Magazine, Vol. 4, pp. 17-21, April, 1988 https://doi.org/10.1109/37.1868
  16. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, 'Learning Internal Representations by Error Propagation', Parallel Distributed Processing, Vol. 1, pp. 318-362, 1986
  17. 오기훈, 주진만, 박광성, 박진배, 최윤호, '신경 회로망을 이용한 혼돈 비선형 시스템의 지능 제어에 관한 연구', 96한국자동제어학술회의 논문집 pp. 453-456, 1996
  18. K. S. Narendra and K. Parthasarathy, 'Idenrification and Control of Dynamical Systems using Neural Networks,' IEEE Trans. Neural Networks, Vol. 1, No. 1, 1990 https://doi.org/10.1109/72.80202
  19. L. A. Aguirre, 'The Use of Identified Models in the Control of a Chaotic Circuit,' IEEE Symposium on Circuits and Systems, Seattle, 1995 https://doi.org/10.1109/ISCAS.1995.521426
  20. L. B. Almeida, 'Backpropagation in Nonfeedforward Networks,' I. Aleksander(Ed.), Neural Computing Architectures, Cambridge, MA, MIT Press, pp. 75-91, 1989
  21. L. Ljung, 'Issue in System Identification,' IEEE Contr. Syst. Mag., Vol. 11, pp. 25-29, 1991 https://doi.org/10.1109/37.103346
  22. P. M. Mills and A. Y. Zomaya, 'A Neural Network Approach to Online Identification of Nonlinear Systems,' Cybernetics and Systems, vol. 24, pp. 171-195, 1993 https://doi.org/10.1080/01969729308961706