Journal of the Korean Society for Precision Engineering (한국정밀공학회지)

Korean Society for Precision Engineering (한국정밀공학회)
권호 표지

Real-time Approximation of a Hydraulic Servo System Using a Recurrent Neural Network with 2-D Learning Algorithm

2차원 학습 회귀적 신경망을 이용한 전기.유압 서보시스템의 실시간 추종

  • 정봉호 (부산대학교 대학원 지능기계공학과) ;
  • 곽동훈 (부산대학교 지능기계공학과) ;
  • 이춘태 (부산대학교 대학원 지능기계공학과) ;
  • 이진걸 (부산대학교 기계공학부)
  • Published : 2003.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents the experiments on the approximation of a hydraulic servo system using a real time recurrent neural networks (RTRN) with time varying weights. In order to verify the effectiveness of the RTRN algorithm in hydraulic servo system, we design the experimental hydraulic system and implemented the real time approximation of system output. Experimental results show that approximated output of the RTRN well follows the position trajectory of the electro-hydraulic servo system. And also it is verified that the 2-D RNN can be implemented in sampling time even though high sampling frequency experimentally.

Keywords

References

  1. Narendra, K. S. and Parthasarathy, K., 'Identification and Control of Dynamic Systems using Neural Networks,' IEEE Trans. Neural Networks, Vol. , No. 1, pp. 4-27, 1990 https://doi.org/10.1109/72.80202
  2. Kurek, J. E. and Zaremba, M. B., ·'Iterative Learning Control Synthesis based on 2-D System Theory,' IEEE Trans. Automat. Contr., Vol. 38, pp. 121-125, 1993 https://doi.org/10.1109/9.186321
  3. Chow, T. W. S. and Fang, Y., 'An Iterative Learning Control Method for Continuous-Time system based on 2-D System Theory,' IEEE Trans. Circuits Syst. I, Vol. 45, pp. 683-689, 1998 https://doi.org/10.1109/81.678496
  4. Chow, T. W. S. and Fang, Y., 'A Recurrent Beural Network based Real-Time Learning Control Strategy Applying to Nonlinear Systems with Unknown Dynamics,' IEEE Trans. Ind. Electronics, Vol. 45, No. 1, pp. 151-161, 1998 https://doi.org/10.1109/41.661316
  5. Chow, T. W. S., Li, X. D. and Fang, Y., 'A Real-Time Learning Control Approach for Nonlinear Continuous-Time System using Recurrent Neural Networks,' IEEE Trans. Ind. Electronics, Vol. 47, No.2, pp. 478-486, 2000 https://doi.org/10.1109/41.836364