An Iterative Learning Control for Noisy Systems by Using Linear Neural Networks

  • Keigo Watanabe
  • Kozo Shiramizu
  • Toshio Fukuda
  • Spyros G. Tzafestas
Part of the Microprocessor-Based and Intelligent Systems Engineering book series (ISCA, volume 9)


By applying a linear neural network, an iterative learning control is described for noisy CARMA (Controlled Autoregressive Moving Average) systems. The developed controller has a form of direct controller in a stochastic environment, while the usual iterative controller has a form of discrete observer in a determine-istic environment. Thus, the present iterative controller can treat with the case of noisy measurements. First, we describe the system considered here and state some assumptions to solve the problem. Next, the model of inverse dynamics is derived and the off-line iterative learning rule is explained by using the delta rule. Then, we show a neural controller, under the situation where the measurement noise is assumed to be known. Furthermore, we describe the method to estimate the noise process on-line by using the associated regular dynamics. Finally, we show some simulation examples to illustrate the features of the present controller. In particular, we shall discuss the results from the view points of the initial connec-tions weights and the generalizability of linear neural networks to some different or untrained reference signals.


Inverse Dynamic Iterative Learning Iterative Learning Control Neural Network Controller Model Reference Adaptive Control 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Antsaklis, P.J., Neural Networks in Control Systems IEEE Control Systems Magazine, April, pp.3–5, 1990Google Scholar
  2. Bien, Z. and Huh, K.M., Higher-order iterative learning control algorithmIEE ProceedingsVol.136 (D), No.3, pp.105–112, 1989zbMATHGoogle Scholar
  3. Lan, M.S. Adaptive Control of Unknown Dynamical Systems via Neural Network ApproachProc. of the 1989 ACCVol.1, pp.910–915, 1989Google Scholar
  4. Li, W. and Slotine, J.E., Neural Network Control of Unknown Nonlinear SystemsProc of the 1989 ACCVol.2, pp.1136–1141, 1989Google Scholar
  5. Miller, W.T., III, Glanz, F.H. and Kraft, E.G., III, Application of a General Learning Algorithm to the Control of Robotic ManipulatorsInt. J. Robotics ResearchVol.6, No.2, pp.84–98, 1987CrossRefGoogle Scholar
  6. Psaltis, D., Sideris, A. and Yamamura, A., A Multilayered Neural Network ControllerIEEE Control SystemsMagazine, April, pp.17–21, 1988Google Scholar
  7. Sugie T. and Ono, T., On a Learning Control LawSystems and ControlVol.31, No.2, pp.129–135, 1987 (in Japanese)Google Scholar
  8. Tokita, M., Mitsuoka, T., Fukuda, T., and Kurihara, T., Force Control of Robotic Manipulator by Neural Network (Experimental Results and their Evaluation of One Degree-of-Freedom Manipula­tor)J. of the Robotics Society of JapanVol.8, No.3, pp.52–59, 1990 (in Japanese)Google Scholar
  9. Watanabe, K., Fukuda, T. and Tzafestas, S.G., An Adaptive Control for CARMA Systems using Linear Neural NetworksProc. of 13th IMACS World Congress on Computation and Applied MathematicsJuly 22–26, Dublin, Ireland, 1991Google Scholar
  10. Widrow, B. and Hoff, M.E., Adaptive switching circuitsInstitute of Radio Engineers Western Electronic Show and Convention Convention Record Part 4pp.96–104, 1960Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 1991

Authors and Affiliations

  • Keigo Watanabe
    • 1
  • Kozo Shiramizu
    • 1
  • Toshio Fukuda
    • 2
  • Spyros G. Tzafestas
    • 3
  1. 1.Department of Mechanical EngineeringFaculty of Science and Engineering, Saga UniversitySagaJapan
  2. 2.Department of Mechanical EngineeringFaculty of Engineering, Nagoya UniversityChikusa-ku, NagoyaJapan
  3. 3.Computer Science Division, National Technical University of AthensZografou, AthensGreece

Personalised recommendations