Recurrent Neural Networks in Linear Systems Controlling
P. C. PATIC1, R. M. ZEMOURI R.2, L. DUŢĂ1
1 Valahia University of Târgovişte,
18-24, Unirii Ave., Târgovişte, Romania
patic@valahia.ro, duta@valahia.ro
2Laboratoire d’Automatique du CNAM,
21, Rue Pinel, 75013 Paris, France
ryad.zemouri@cnam.fr
Abstract: This paper presents an application of an ANN (Artificial Neural Network) of a RNRF type (Recurrent Network with Radial basis Function) in controlling a linear system. The performance of ANN-based control solution is compared with a classic controller and the results show that ANN behaves better than the classic controller. MATLAB simulation performed show that the coupling between the ANN and a proportional controller gives the best performance.
Keywords: Human-machine interface, usability criteria, end-user development, risks.
>Full text
CITE THIS PAPER AS:
P. C. PATIC, R. M. ZEMOURI R., L. DUŢĂ, Recurrent Neural Networks in Linear Systems Controlling, Studies in Informatics and Control, ISSN 1220-1766, vol. 19 (2), pp. 153-158, 2010.
1. Introduction
The linear systems control is today an important research and development area in control engineering. In the real world, however, many processes are characterized by a nonlinear dynamic behavior which makes impossible to use conventional tools for automatic control. The same applies to systems for which mathematical models are incompletely specified or of a poor quality. There is currently no systematic theory to be applied to control such processes. To solve this problem, one solution is to use a learning phase to identify the process model or controller. The term ‘learning’ is about changing the structure and/or system settings in order to improve its future performance, based on previous experimental observations [1, 4]. Some adaptive controlling methods have been developed, to enable the evolution of controller depending on the task [3, 9]. The structure of the controller being already chosen, those methods allow fixing a number of parameters of this one. If the general principle used by these algorithms is similar to learning done by ANN, adaptation is done by a simple setting of a small number of coefficients of the control loop without storage capacity [5]. Systems with learning characteristics such as ANN (Artificial Neural Networks) can be successfully utilized in control problems such as the decision support or situation recognition [4, 6, 12, 13]. In this case we speak about learning in command rather than adaptive control.
This article consists of three parts. Section I reviews a dynamic variation of ANN that one of the authors of this paper proposed in a previous work [21]. Section II presents the basic principles and some methods of neurons control technique. Finally, Section III presents the tests and the obtained experimental results.
REFERENCES
- Baker, W. L., J. A. Farrell, An Introduction to Connectionist Learning Control Systems, In D. A. White and D. A. Sofge, editors, Handbook of Intelligent Control, Van Nostrand Reinhold Ed., 1992, pp. 35-64.
- Chappelier, J. C., RST: une architecture connexionniste pour la prise en compte de relations spatiales et temporelles, Thèse de doctorat, Ecole Nat. Sup. des Télécomm., 1996.
- Costaftis, M., Comportement et contrôle des systèmes complexes: introduction aux méthodes algébriques, qualitatives et fonctionnelles, Diderot éd., Arts et Sciences, 1997.
- Elfelly, N., J.-Y. Dieulot, P. Borne, A Neural Approach of Multi-model Representation of Complex Systems, International. Journal of Computers Communication & Control-IJCCC vol. 3, no. 2, 2008, pp. 149-160.
- Elman, J. L., Finding Structure in Time, Cognitive Science, vol. 14, 1990, pp. 179-211.
- Filip, F. G., K. Leiviiska, Large-scale complex systems, Springer Handbook of Automation (S. Y. Nof , Ed.). Springer, Berlin, 2009, pp. 619-638.
- Gauthier, E., Utilisation des Réseaux de Neurones Artificiels pour la Commande d’un Véhicule Autonome, Thèse de doctorat, Institut National Polytechnique de Grenoble, Janvier 1999.
- Ivanescu, M., M. C. Florescu, The Control of Hyper-redundant Manipulators by Frequency Criteria, Studies in Informatics and Control vol.18, no3, 2009, pp. 279-288.
- Jordan, M. I., D. E. Rumelhart, Forward Models: Supervised Learning with a Distal Teacher, Cognitive Science, vol. 16, 1992, pp. 307-354.
- Kawato, M., Schemes and Models for Control of Arm Trajectory, In W. T. Miller, R. S. Sutton, and P. J. Werbos editors, Neural Networks for Control, MIT Press, 1990, pp. 197-228.
- Narendra, K., A. M. Annaswamy, Stable Adaptive Systems, Prentice-Hall, Englewood, NJ, 1989.
- Narendra, K. S., K. Parthasarathy, Identification and Control of Dynamical Systems Using Neural Networks, IEEE Transactions on Neural Networks, vol 1(1), 1990, pp. 4-5.
- Patic, P. C., Neural Approaching of the Materials Processing Establishing Problem, Scientific Bulletin of the Electrical Engineering Faculty, 2006, pp. 57-59.
- Pomerleau, D. A., Neural Network Perception for Mobile Robot Guidance, Kluwer Academic Press, 1993.
- Psaltis, D., A. Sideris, A. Yamamura, A Multi-layer Neural Network Controller, IEEE Control Systems Magazine, no. 8, 1988, pp. 17-21.
- Simpson, P. K., Fuzzy Min-max Neural Networks – Part II: Clustering, IEEE Transaction on Fuzzy Systems, Vol.1, 1993, pp. 32-45.
- Stergiou, C., D. Siganos, Neural Networks, (http://www.docstoc.com/ docs/15050/NEURAL-NETWORKS-by-Christos-Stergiou-and-Dimitrios-Siganos) on-line 2007
- Widrow, B., F. W. Smith, Pattern-Recognizing Control Systems, Proceeding of Computer and Information Sciences, 1964.
- Zemouri, R., D. Racoceanu, N. Zerhouni, Recurrent Radial Basis Function Network for Time-Series Prediction, Engineering Applications of AI, The International Journal of Intelligent Real-Time Automation, journal IFAC, Elsevier Science, vol. 16, Issue 5-6, 2003, pp. 453-463.
- Zemouri, R., D. Racoceanu, N. Zerhouni, Réseaux de neurones à fonctions de base radiales: application au pronostic, Revue des sciences et technologies de l’information – RSTI, série Revue d’intelligence artificielle- RIA, vol. 16, nr. 13/2002, ISBN: 2-7462-0568-8, Ed. Hermès – Lavoisier, Paris, 2002, pp. 307-338.
- Zemouri, R., Contribution à la surveillance des systèmes de production à l’aide des réseaux de neurones dynamiques: Application à la e-maintenance, Thèse de doctorat, Université de Franche-Comté, Nov. 2003
- Zhang, Y., P. Sen, G. E. Hearn, An On-line Trained Adaptive Neural Controller, IEEE Control Systems Magazine, vol. 15(5), 1995, pp. 67-75.