Hardware-based neural identification: Linear dynamical systems
- 32 Downloads
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 wordsSystem identification Neurocomputer Digital neural network VLSI chip
Unable to display preview. Download preview PDF.
- 1.Eykoff P (1974) System identification-parameter and state estimation. Wiley, LondonGoogle Scholar
- 2.Kagiwada HH (1974) System identification methods and application. Addison-Wesley, Reading, MassGoogle Scholar
- 3.Nakano K, Iinuma K, neuron-net-group, Kiritani S (1989) Introduction and exercise for neurocomputers (in Japanese). Gizyutsuhyoronnsha, TokyoGoogle Scholar
- 4.Kikuti T (1990) Introduction for neurocomputers (in Japanese). Ohmusha, TokyoGoogle Scholar
- 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.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
- 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
- 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.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