Journal of the Institute of Electronics Engineers of Korea SC (전자공학회논문지SC)

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

On Designing a Control System Using Dynamic Multidimensional Wavelet Neural Network

동적 다차원 웨이브릿 신경망을 이용한 제어 시스템 설계

  • Cho, Il (Dept. of Electronic Eng., Chung-Ang Univ.) ;
  • Seo, Jae-Yong (Dept. of Electronic Eng., Chung-Ang Univ.) ;
  • Yon, Jung-Heum (Dept. of Electronic Eng., Chung-Ang Univ.) ;
  • Kim, Yong-Taek (Dept. of Electronic Eng., Chung-Ang Univ.) ;
  • Jeon, Hong-Tae (Dept. of Electronic Eng., Chung-Ang Univ.)
  • 조일 (중앙대학교 전자공학과) ;
  • 서재용 (중앙대학교 전자공학과) ;
  • 연정흠 (중앙대학교 전자공학과) ;
  • 김용택 (중앙대학교 전자공학과) ;
  • 전홍태 (중앙대학교 전자공학과)
  • Published : 2000.07.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, new neural network called dynamic multidimensional wavelet neural network (DMWNN) is proposed. The resulting network from wavelet theory provides a unique and efficient representation of the given function. Also the proposed DMWNN have ability to store information for later use. Therefore it can represent dynamic mapping and decreases the dimension of the inputs needed for network. This feature of DMWNN can compensate for the weakness of diagonal recurrent neural network(DRNN) and feedforward wavelet neural network(FWNN). The efficacy of this type of network is demonstrated through experimental results.

본 논문에서는 동적 다차원 웨이블릿 신경망을 제안한다. 웨이블릿 이론을 이용한 DMWNN은 근사화 대상함수를 유일하고 효과적으로 표현할 수 있으며, 추후에 사용할 수 있는 정보를 저장하는 능력을 가지고 있다. 따라서 DMWNN은 동적 매핑이 가능하고, 필요한 입력의 차원을 줄일 수 있는 장점이 있다. DMWNN은 대각 귀환신경망과 전방향 웨이블릿 신경망의 단점을 보완하여 설계하였다. 제안한 DMWNN의 우수성을 실험을 통해 검증하였다.

Keywords

References

  1. Chao-Chee Ku, Kwang Y. Lee, 'Diagonal Recurrent Neural Networks for Dynamic Systems Control', IEEE Trans. Neural Network, vol. 6, pp. 144-156, Jan. 1995 https://doi.org/10.1109/72.363441
  2. 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, June. 1995 https://doi.org/10.1109/78.388860
  3. Q. Zhang and A. Benveniste, 'Wavelet networks,' IEEE Trans. Neural Networks, vol. 3, pp. 889-898, Nov. 1992 https://doi.org/10.1109/72.165591
  4. Y. C. Pati and P. S. Krishnaprasad, 'Analysis and synthesis of foodforward neural network using discretc affine wavelet transformations', IEEE Trans. on Neural Network, vol. 4, pp. 73-85, Jan. 1993 https://doi.org/10.1109/72.182697
  5. K. Hornik, M. Stinchcombe and H. White, 'Multilayer feedforward networks are universal approximators,' Neural Networks, vol. 2, pp. 359-366, 1989 https://doi.org/10.1016/0893-6080(89)90020-8
  6. Ah chung Tsoi, Andrew D. Back, 'Locally Recurrent Globally Feedforward Networks: A Critical Review of Architectrues', IEEE Trans. Neural Network, vol. 5, pp. 229-239, March. 1994 https://doi.org/10.1109/72.279187
  7. Yi Cheng, T. W. Karjala, David M. Hlmmelblau, 'Closed Loop Nonlinear Process Identification Using Internally Recurrent Nets', Neural Networks, vol. 10, pp. 571-596, July. 1997 https://doi.org/10.1016/S0893-6080(96)00097-4
  8. C. S. Burrus, R. A. Gopinath, and H. Guo, Introduction to Wavelets and Wavelet Transforms. Upper Saddle River, NT:Prentice-Hall, 1998
  9. Madan M. Gupta, Dandina H. Rao, Neuro-Control Systems Theory and applications, IEEE PRESS, vol. a selected reprint, 1994
  10. Yoan D. Landau, Adaptive Control, The Model Reference Approach, Marcel Dekker, Inc., 1979
  11. Eduardo Liceaga-Castro, Gerrit M. van der Molen, 'Submarine $H^{\infty}$ Depth Control Under Wave Disturbances', IEEE Trans. Control Systems Technology, vol. 3, pp. 338-379, Sep. 1995 https://doi.org/10.1109/87.406981
  12. Ah chung Tsoi, Shaohua Tan, 'Recurrent neural networks:A constructive algorithm, and its properties', Neurocomputing 15, 1997, 309 326. 1345-1350, 1995 https://doi.org/10.1016/S0925-2312(97)00011-8
  13. J. Ludik, W. Prins, K. Meert, T. Catfolis, 'A Comparative Study of Fully and Partially Recurrent Networks', Proceedings of the 1997 International Conference on Neural Networks, vol. 1, V.1, 1997-06-09 https://doi.org/10.1109/ICNN.1997.611681
  14. Jean-Philippe S. Draye. Davor A. Pavisic, Guy A. Cheron, Gaetan A. Libert, 'Dynamic Recurrent Neural Networks: A Dynamical Analysis', IEEE Trans. Systems, Man and cybernetics, vol. 26, pp. 692-706, Oct. 1996 https://doi.org/10.1109/3477.537312
  15. J. S. R. Jang, C. T. Sun, E. Mizutani, Neuro-Fuzzy and Soft Computing, Prentice-Hall, Inc., 1997
  16. 김성현, 최중락, 심귀보, 전홍태, '수중운동체를 위한 퍼지 가중치를 갖는 뉴럴 제어기 설계', 대한전자공학회 논문지, 제 33권 B편, 제3화, pp. 151-158, 1996년 3월
  17. 김성현, '불확실한 비선형 동적시스템의 강건한 적응 퍼지-신경망 제어 및 로보트 매니퓰레이터에의 적용', 중앙대학교 전자공학과 박사학위 논문, 제 60회, 1996
  18. 서승진, '비선형 시스템의 안정한 직접 적응 제어를 위한 웨이브렛 신경회로망', 중앙대학교 전자공학과 석사학위 논문, 제 90회, 1998