Journal of Institute of Control, Robotics and Systems (제어로봇시스템학회논문지)

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지

Adaptive PID controller based on error self-recurrent neural networks

오차 자기순환 신경회로망에 기초한 적응 PID제어기

  • 이창구 (전북대학교 전기.전자 제어공학부) ;
  • 신동용 (한라전문대학교 방사선과)
  • Published : 1998.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we are dealing with the problem of controlling unknown nonlinear dynamical system by using neural networks. A novel error self-recurrent(ESR) neural model is presented to perform black-box identification. Through the various outcome of the experiment, a new neural network is seen to be considerably faster than the BP algorithm and has advantages of being less affected by poor initial weights and learning rate. These characteristics make it flexible to design the controller in real-time based on neural networks model. In addition, we design an adaptive PID controller that Keyser suggested by using ESR neural networks, and present a method on the implementation of adaptive controller based on neural network for practical applications. We obtained good results in the case of robot manipulator experiment.

Keywords

References

  1. IEEE Trans. Neural Networks v.1 Identification and control of dynamical systems using neural networks K. S. Narendra;Patthasarathy
  2. Proc. IEEE Int. Conf. Systems Engineering A system identification technique based on neural networks H. Wabgaonkar;A. Stubberud
  3. Parallel Distributed Processing v.1 D. E. Rumelhart;J. L. McClelland
  4. Automatica v.28 no.6 Artificial neural networks in process estimation and control M. J. Wills(et al.)
  5. Automatica v.28 no.6 Neural networks for control systems-A survey K. J. Hunt;D. Sbararo;P. J. Gawthrop
  6. Trans IChemE v.72 Artificial neural networks : studies in process modelling and control A. J. Morris;G. A. Montague;M. J. Willis
  7. IEEE Control system Model predictive control using neural networks A. Draeger;S. Engell;H. Ranke
  8. The Canadian J. of ChemE v.72 The design of experiments, training and implementation of nonlinear controllers based on neural networks B. S. Dayal;P. A. Taylor;J. F. Macgregor
  9. Int. Symposium on Intelligent Control Neural model predictive control of nonlinear chemical process H.-T. Su;T. J. McAvoy
  10. Neural Networks : A Comprehensive Foundation S. Haykin
  11. Proc. IEEE Int. Conf. Acoustic, Speech, Signal Processing Training feedforward networks with the extended Kalman algorithm S. Singhal;L. Wu
  12. IEEE Trans. Signal Processing v.40 A fast new algorithm for training feedforward neural networks R. S. Scalero;N. Tepedelenliouglu
  13. 대한전기학회 논문지 v.48 no.12 오차순환 신경회로망을 이용한 빠른 시변비선형 시스템의 인식과 제어 이창구
  14. ACC'94 Artificial neural network model based control G. A. Montague;M. J. Willis;Morris
  15. CONTROL'94 Adaptive PID control with neural network based predictor R. D. Keyser;Yonghong Tan