Hybrid GA-PID WAVENET 제어기를 이용한 모형 헬리콥터 시스템의 자세 제어

Attitude Control of Helicopter Simulator System using A Hybrid GA-PID WAVENET Controller

  • 박두환 (동아대학교 대학원 전기공학과) ;
  • 지석준 (동아대학교 대학원 전기공학과) ;
  • 이준탁 (동아대학교 공과대학 전기전자컴퓨터공학부)
  • 발행 : 2004.06.01

초록

The Helicopter Simulator System is non-linear and complex. Futhermore, because of absence of its accurate mathematical model, it is difficult to control accurately its attitudes such as elevation angle and azimuth one. Therefore, we proposed a Hybrid GA-PID WAVENET(Genetic Algorithm Proportional Integral Derivative Wavelet Neural Network)control technique to control efficiently these angles. The proposed Hybrid GA-PID WAVENET is made through the following process. First, the WAVENET fundamental functions are defined. And their dilation and translation values are adjusted by GA to construct the optimal WAVENET controller. Secondly, the proportional, integral, and derivative gain coefficients of PR controller are tuned optimally. Finally, WAVENET controller which has a good transient characteristic and GA-PE controller which has a good steady state characteristic is adequately combined in hybrid type. Through the computer simulations, it is proved that the Hybrid GA-PE WAVENET control technique has a more excellent dynamic response than PID control technique and GA-PID one.

키워드

참고문헌

  1. B. Srinivasan, P. Mullhaupt, T. Baumann, and D.Bonvin. 'A discrete-time decoupling scheme for a differentially cross-coupled system', 13th IFAC Trennial World Congress, San Francisco, pp 301-306, 1996
  2. Mats Akesson, Erik Gustafson and Karl Henrik Johansson. 'Control Design for a Helicopter Lab Process' IFAC. 13th Triennial World Congress, San Francisco, USA, pp. 41-46, 1996
  3. P. Mullhaupt, B. Srinivasan, and D. Bonvin. 'A Two-time-scale Controller for a Differentially Cross-coupled system.' Proceedings of the American Control Conference Albuquerque, New Mexico. pp. 3839-3841, 1997 https://doi.org/10.1109/ACC.1997.609574
  4. A. J. Calise, J. V. R Prasad, 'Helicopter Adaptive Flight Control Using Neural Network', Proceedings of the 33rd Conference on Decision and Control, Lake Buena Vista, pp. 3336-3340, 1994 https://doi.org/10.1109/CDC.1994.411659
  5. D.P.Salts, A Sideris and AA Yamamura 'A multi layered neural network controller.' IEEE Control system Magazine, No 2, pp. 17-21, 1988 https://doi.org/10.1109/37.1868
  6. Rumelhart. D.E., Hinton. G.E. and Williams. R.J. 'Learning internal representation by error propagation', Paraller Distributed Processing, Vol. 1, MIT Press, pp. 318-362, 1986
  7. David E. Goldberg, Genetic Algorithms in Searching, Optimization & Machine Learning, Addison-Wesley, 1989
  8. M. Sugeno and T. Yasukawa, 'Fuzzy model identification and self-learning for dynamic system', IEEE Trans. Fuzzy Syst., vol. 1, pp.7-31, 1993 https://doi.org/10.1109/TFUZZ.1993.390281
  9. G. Lightbody, 'Direct neural model reference adaptive control', lEE Proc, Control Theory appl, vol. 142, No 2, pp. 661-657, 1995
  10. Chia- Ju Wu and Ching-Huo Huang, 'A Hybrid Method for Parameter Tuning of PID Controllers', J. Franklin Inst., vol. B334, No.4, pp. 547-562, 1997 https://doi.org/10.1016/S0016-0032(96)00094-4
  11. Rong- Jong Wai, Jia-Ming Chang, 'Intelligent control of induction servo motor drive via wavelet neural network', Electric Power System Research 61, pp. 67-76, 2002 https://doi.org/10.1016/S0378-7796(01)00190-0
  12. J. Zhang, G. G. Walter, Y. Miao and W. N. W. Lee, 'Wavelet neural networks for function learning', IEEE Trans. Signal Processing, vol. 43, pp. 1485-1497, 1995 https://doi.org/10.1109/78.388860
  13. Mitsuo Gen, Runwei Cheng, 'Genetic Algorithms & Engineering Design', Wiley, 1997
  14. Collins, R, Jefferson, D., 'Selection Parallel Genetic Algorithm', International Conf. on Genetic Morgan-Kaufmann, pp. 249-256, 1991
  15. L.Ljung,' Asymptotic variances expressions for identified black-box transfer function modes', IEEE Trans. Automatic Control. pp. 834-844, 1985 https://doi.org/10.1109/TAC.1985.1104093
  16. L.Ljung and Z.D.Yuan, 'Asymptotic properties of black-box identification of transfer functions', IEEE Trans. Autom. Control, vol. AC-30, pp. 514-530, 1985 https://doi.org/10.1109/TAC.1985.1103995