Neural Network-Based System Identification and Controller Synthesis for an Industrial Sewing Machine

  • Kim, Il-Hwan (Department of Electrical and Computer Engineering, Kangwon National University) ;
  • Stanley Fok (Department of Electrical and Computer Engineering, University of Waterlo) ;
  • Kingsley Fregene (Department of Electrical and Computer Engineering, University of Waterlo) ;
  • Lee, Dong-Hoon (Department of Electrical and Computer Engineering, Kangwon National University) ;
  • Oh, Tae-Seok (Department of Electrical and Computer Engineering, Kangwon National University) ;
  • David W. L. Wang (Department of Electrical and Computer Engineering, University of Waterloo)
  • Published : 2004.03.01

Abstract

The purpose of this paper is to obtain an accurate nonlinear system model to test various control schemes for a motion control system that requires high speed, robustness and accuracy. An industrial sewing machine equipped with a Brushless DC motor is considered. It is modeled by a neural network that is configured as an output-error dynamical system. The identified model is essentially a one step ahead prediction structure in which past inputs and outputs are used to calculate the current output. Using the model, a 2 degree-of-freedom PID controller to compensate the effects of disturbance without degrading tracking performance has been de-signed. In this experiment, it is not preferable for safety reasons to tune the controller online on the actual machinery. Experimental results confirm that the model is a good approximation of sewing machine dynamics and that the proposed control methodology is effective.

Keywords

References

  1. IEEE Trans. on Industrial Electronics v.47 A two-degrees-of-freedom current control scheme for deadtime compensation N. Hur;K. Nam;S. Won https://doi.org/10.1109/41.847896
  2. Master's Thesis, University of Waterloo Investigation On a Haptic Device for Teleoperation G. M. Y. Lai
  3. Master's Thesis, University of Waterloo Development of an Internet Visual Telepresence System C. F. Turner
  4. IEEE Trans. on Automat. Contr. v.AC-31 General solution of robust tracking problem in two-degree-of-freedom control system T. Sugie;T. Yoshikawa
  5. System and Control v.29 Two-degree-of-freedom controller I-PID, differential feedforward, I-PD controller K. Araki
  6. IEEE Trans. on Fuzzy Systems v.9 no.2 Modeling, identification, and control of a class of nonlinear systems Zhang Huaguang;Quan Yongbing https://doi.org/10.1109/91.919256
  7. Mechatronics v.10 Experimental identification of universal motor dynamics using neural networks K. K. Safak;O. S. Turkay https://doi.org/10.1016/S0957-4158(99)00095-1
  8. IEEE Trans. on SMC v.26 no.4 Discrete time neural network synthesis using input and output activation functions B. M. Novakovic
  9. IEEE Trans. on Mechatronics v.6 no.2 Intelligent modeling, observation, and control for nonlinear systems D. Schroder;C. Hintz;M. Rau https://doi.org/10.1109/3516.928725