SciELO - Scientific Electronic Library Online

 
vol.6 issue4Hopf Bifurcations: Qualitative Analysis and Application to a Bioeconomic Model of FisheriesQualitative Interpretation of Camera Motion in the Projection of Individual Frames of an Image Stream author indexsubject indexsearch form
Home Pagealphabetic serial listing  

Services on Demand

Journal

Article

Indicators

Related links

  • Have no similar articlesSimilars in SciELO

Share


Computación y Sistemas

Print version ISSN 1405-5546

Comp. y Sist. vol.6 n.4 México Apr./Jun. 2003

 

Artículos

 

Control Neuronal por Modelo de Referencia para un Sistema de Estructura Variable

 

Model Reference Neural Control of a Variable Structure System

 

M. Margarita Goire C1, J. Martín Flores A.2, Moisés Bonilla3, Ieroham S. Baruch3

 

1 Facultad de ingeniería Eléctrica, Departamento de Informática
2 Secretaría de Marina, Armada de México
3 Centro de Investigación y Estudios Avanzados
Departamento de Control Automático

 

E–mails: mgoireie@fie.uo.edu.cu, cuenta02@prodigy.net.mx, mbonilla@enigma.red.cinvestav.mx, baruch@ctrl.cinvestav.mx

 

Artículo recibido en Junio 15, 2000; aceptado en Abril 10, 2003

 

Resumen

El objetivo de este trabajo es presentar una propuesta de control neuronal por modelo de referencia para un sistema que cambia su estructura interna de un sistema lineal de primer orden a un sistema lineal de segundo orden, aplicando para esta tarea una red neuronal recurrente. Se presentan dos esquemas de control neuronal por modelo de referencia para el sistema antes mencionado. Una de las características de la red neuronal que se utiliza es la de tener restricciones en sus pesos, esto garantiza su estabilidad durante el entrenamiento. En el primer esquema se utiliza una red neuronal para la identificación del sistema de estructura variable: en el segundo esquema se usan dos redes neuronales con el propósito de separar la identificación de cada subsistema.

Palabras Clave: Redes Neuronales, Sistemas de Estructura Variable, Control por Modelo de Referencia, Control Inteligente, Sistemas implícitos.

 

Abstract

The objective of this paper is to propose a reference model neural control of a system, which change its internal structure from a linear system of first order to a linear system of second order, applying for this task a recurrent neural network. Two schemes of reference model neural control, for the above mentioned system, are presented. One characteristic feature of the neural network used, is that a feedback weight restriction is applied, which preserved its stability during the learning The first control scheme uses one neural network for identification of the variable structure system; the second control scheme uses two neural networks so to separate the identification of each subsystem.

Keywords: Neural Networks, Variable Structure Systems, Model Reference Control, Intelligent Control, Implicit Systems.

 

DESCARGAR ARTICULO EN FORMATO PDF

 

Referencias

I. S. Baruch, J.M. Flores, F. Nava, I.R. Ramirez, and B. Nenkova, "An Adavanced Neural Network Topology and Learning, Applied for Identification and Control of a D.C. Motor", in Proc. of the First Int. IEEE Symposium on Intelligent Systems, Varna, Bulgaria, Sept., 2002, pp. 289–295.        [ Links ]

I. S. Baruch, J. M. Flores, R. Garrido, and E. Gortcheva, "Identificación de sistemas no lineales complejos usando un multimodelo neuronal difuso", in Científica, ESIME, No.19, Ene–Feb., 2000, pp.29–40.        [ Links ]

I. Baruch, J.M. Flores, F. Thomas, and R. Garrido, Adaptive Neural control of Nonlinear Systems, in Proc. of the Artificial Neural Networks Conf –ICANN 2001, Lecture Notes in Computer Science, vol. 2130, G. Dorfner, H. Bischof and K. Hornik, Eds. Berlin, Heidelberg, New York Springer–Verlag, 2001, pp. 930–936.        [ Links ]

M. Bonilla, and M. Malabre, "Variable Structure Systems via implicit Descriptions", in Proceedings of the 1st European Control Conference, Grenoble, France, Vol. 1, pp. 757–761, 2–5 July, 1991.        [ Links ]

M. Bonilla, G. Lebret, and M. Malabre, "Output Dynamics Assignment for Implicit Descriptions", in Circuits, Systems and Signal Processing, Special Issue on Implicit Robust Systems, Vol. 13 No. 2–3, 1994, pp. 349–359.        [ Links ]

M. Bonilla, M. Fonseca M, and M. Malabre, "On the Implementation of some Variable Structure Systems Control Laws (the case of two points variating systems)", in Proceedings of the 32–nd IEEE CDC, San Antonio, Texas, USA, 1993, pp. 895–896.        [ Links ]

M. Bonilla E., M. M. Goire, and S. Mondié, "Adaptive Structure Detector", in Proc. of the American Control Conference ACC'2000, Chicago, USA, June, 2000.        [ Links ]

M. Goire, M. Bonilla, S. Mondié, "Neural Network Reconstructor for Implicit Systems", in Proc. American Control Conference ACC''2000, Chicago, USA, June 2000.        [ Links ]

M. M. Goire, M. Bonilla, and S. Mondié, "Sur l'apprentissage des rseaux de neurones pour la reconstruction de la structure de systémes implicites", in Proc. Conference Internationale Francophone d'Automatique CIFA'2000, Lille, France, Juillet, 2000.        [ Links ]

F.L. Lewis, "A Tutorial on the Geometric Analysis of Linear Time–invariant Implicit Systems", in Automatica, Vol.28, No. 1, 1992, pp. 119–137.        [ Links ]

F.  L. Lewis, "A Survey of Linear Singular Systems", in Circuits, Systems and Signal Proc, No. 9, September, 1991, pp. 3–36.        [ Links ]

K. Narendra, and K. Parthasarathy, "Identification and Control of Dynamical Systems Using Neural Networks", in IEEE Transactions on Neural Networks, Vol. 1, No. 1. March, 1990, pp. 4–27.        [ Links ]

A. S. Poznyak, E. N Sánchez, and W. Yu, Differential Neural Networks for Robust Nonlinear Control, World Scientific, Singapore, 2001.        [ Links ]

G.  A. Rovithakis, and M. A. Christodoulou, Adaptive Control with Recurrent High–Order Neural Networks, Springer Verlag, New York, USA, 2000.        [ Links ]

J. A. K. Suykens, L, Vandewalle, and R. de Moor, Artificial Neural Networks for Modelling and Control of Nonlinear Systems, Kluwer Academic Publishers, Boston, USA, 1996.        [ Links ]

Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License