Advertisement

Artificial Life and Robotics

, Volume 1, Issue 3, pp 151–155 | Cite as

Hardware-based neural identification: Linear dynamical systems

  • Masanori Sugisaka
  • Shuuji Motomura
  • Takashi Kitaguchi
  • Toshiyuki Furuta
  • Hirotosi Eguchi
Original Paper

Abstract

In this paper, a hardware-based neural identification method is proposed in order to learn the characteristics or structure of a discrete linear dynamical system. Quick or instant identification of unknown dynamical systems is particularly required for practical controls not only in intelligent mechatronics such as, for example, automatic selforganized running of mobile vehicles, but in intelligent self-controlled systems. We developed a new method of hardware-based identification for general dynamical systems using a digital neural network very large scale integration (VLSI) chip, RN-200, where sixteen neurons and a total of 256 synapses are integrated in a 13.73×13.73 mm2 VLSI chip, fabricated using RICOH 0.8 μm complementary metal oxide semiconductor CMOS technology (RICOH, Yokohama, Japan). This paper describes how to implement neural ideitification in both learning and feedfoward processing (recognizing) using a RICOH RN-2000 neurocomputer which consists of seven RN-200 digital neural network VLSI chips.

Key words

System identification Neurocomputer Digital neural network VLSI chip 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Eykoff P (1974) System identification-parameter and state estimation. Wiley, LondonGoogle Scholar
  2. 2.
    Kagiwada HH (1974) System identification methods and application. Addison-Wesley, Reading, MassGoogle Scholar
  3. 3.
    Nakano K, Iinuma K, neuron-net-group, Kiritani S (1989) Introduction and exercise for neurocomputers (in Japanese). Gizyutsuhyoronnsha, TokyoGoogle Scholar
  4. 4.
    Kikuti T (1990) Introduction for neurocomputers (in Japanese). Ohmusha, TokyoGoogle Scholar
  5. 5.
    Sugisaka M, Kodama Y, Sagra S, Ueno S, Kagiwada HH (1990) Characters recognition via artificial neural systems. Proceedings of the International Conference of Fuzzy Logic and Neural Networks, IIZUKA '90, Kyushu Institute of Technology, Iizuka. Fukuoka, Japan, July 22–24 1990, pp. 311–314Google Scholar
  6. 6.
    Sugisaka M, Sagara S Ueno S (1990) Patterns recognition via artificial neural network systems. Proceedings of the 1990 Korean Automatic Control Conference, Korean Association of Automatic Control, Seoul, Korea, October 26–27 1990, pp 929–932Google Scholar
  7. 7.
    Sugisaka M, Ino M (1994) A neuro identifier for linear and nonlinear systems. Systems Sci 20(3):55–64MathSciNetGoogle Scholar
  8. 8.
    Sugisaka M, Ino M (1994) Model predictive control based on neural identification method. Comput Math Applic 27 (9/10):83–93MATHMathSciNetCrossRefGoogle Scholar
  9. 9.
    Richalet J, Rault A, Testud JL, Papon J (1978) Model predictive heuristic control: application to industrial processes. Automatica 14:413–428CrossRefGoogle Scholar
  10. 10.
    Takamatsu T, Hashimoto I, Ohshima M, Ohno H (1987) A study of model predictive control in term of its structure and degree of freedom (in Japanese), Kagakukougaku 13(1):71–77Google Scholar
  11. 11.
    Sugisaka M, Goto F, Sagara S, Ueno S, Fischl R, (1994) Model predictive control with command generator for nonlinear systems. Systems Sci 20(4):25–30MathSciNetGoogle Scholar
  12. 12.
    Oteki S, Hashimoto A, Furuta T, Motomura S, Watanabe T, Stork DG, Eguchi H (1993) A digital neural network VLSI with on-chip learning using stochastic pulse encoding. Proceeding of 1993 International Conference on Neural Networks, Nagoya, Japan, October 25–29 1993, pp 3029–3045Google Scholar
  13. 13.
    Sugisaka M, Hara M, Tonoya N, Ike Y, Hatanaka N, Kim SW, Lee JJ (1994) Running tests of a mobile vehicle. Proceedings of 1st Asian Control Conference, Tokyo Metropolitan Institute of Technology, Tokyo, Japan, July 27–30 1994, pp 439–442Google Scholar

Copyright information

© ISAROB 1997

Authors and Affiliations

  • Masanori Sugisaka
    • 1
  • Shuuji Motomura
    • 2
  • Takashi Kitaguchi
    • 2
  • Toshiyuki Furuta
    • 2
  • Hirotosi Eguchi
    • 2
  1. 1.Department of Electrical and Electronic EngineeringOita UniversityOitaJapan
  2. 2.Research and Department Center CCRGRICOH Co., Ltd.YokohamaJapan

Personalised recommendations