Información del artículo
Resumen
Este artíulo trata sobre el control IMC no lineal y un método para hacerlo tolerante a los fallos en la planta. El control IMC no lineal se consigue por medio de modelos no lineales de la planta y de la inversa de la dinámica de la misma. Ambos se hacen mediante redes neuro-difusas del tipo ANFIS. La tolerancia a los fallos abruptos e incipientes en la planta se consigue mediante la adición de una señal de control compensadora. Ésta se calcula mediante una red neuronal que se entrena en línea a partir de la minimizaciñn del error de control. Se muestran resultados en simulaciñn para una planta de control de pH.
Palabras clave:
IMC
redes neuronales
control no lineal
control tolerante a fallos
El Texto completo está disponible en PDF
Referencias
[Boukezzoula et al., 2003]
Reda Boukezzoula, Galichet Sylvie, Foulloy Laurent.
Nonlinear internal model control: Application of inverse model based fuzzy control.
IEEE Transactions on Fuzzy Systems, 11 (2003), pp. 814-829
[Chen et al., 1999]
J. Chen, Ron J. Patton, Z. Chen.
Active fault tolerant flight conrol systems design using the linear matrix inequality method.
Transactions of the Institute of Measurement Control, 21 (1999), pp. 77-84
[Cui et al., 1993]
Xianzhong Cui, Kang G. Shin.
Direct control and coordination using neural networks.
IEEE Transactions on Systems, Man and Cybernetics, 23 (1993), pp. 686-697
[de Prada et al., 1984]
César. de Prada, Vega. Pastora, Alonso. Luis.
Modelling and simulation of a sulfitation tower for adaptive control.
11th F IASTED conference Applied Modelling Simulation,
[Economou et al., 1986]
C.G. Economou, Morari. Manfred, B.O. Palsson.
Internal model control 5. extension to nonlinear systems.
Industrial Engineering Chemical Process Design and Development, 25 (1986), pp. 403-411
[Edgar et al., 1999]
Craig R. Edgar, Bruce E. Postlethwaite.
Using fuzzy relational models for control.
Prceedings of the European Sysmposium on Intelligent Techniques,
[Fink et al., 2002]
Alexander. Fink, Nelles. Oliver, Isermann. Rolf.
Nonlinear internal model control for MISO systems based on local linear neurofuzzy models.
Proceedings of the 15th IFAC World Congress,
[Fuente et al., 2005]
M.J. Fuente, G.I. Sáinz, M. Alonso, A. Aguado.
Neuro-fuzzy control of a pH plant.
Proceedings of the 16th IFAC World Congress,
[Gao and Antsaklis, 1991]
Z. Gao, P.J. Antsaklis.
Stability of the pseudo-inverse method for reconfigurable control systes.
International Journal Control, 53 (1991), pp. 717-729
[García and Manfred Morari, 1982]
C.E. García, Manfred Morari.
Internal model control – 1. a unifiying review and some new results.
Ind. Eng. Chem. Process Des. Dev., 21 (1982), pp. 308-328
[Haykin and Simon, 1999]
Simon. Haykin.
Neural Networks: a Comprehensive Foundation.
2ª, Prentice Hall International Inc, (1999),
[Hirschorn and Ronald, 1979]
Ronald M. Hirschorn.
Invertibility of multivariable nonlinear control systems.
IEE Transactions on Automatic Control, 24 (1979), pp. 855-865
[Hunt and Sbarbaro, 1991]
K.J. Hunt, D. Sbarbaro.
Neural networks for nonlinear internal model control.
IEE Proceedings–D (IEE, Ed.),
[Hunt et al., 1992]
K.J. Hunt, D. Sbarbaro, R. Zbikowski, P.J. Gawthrop.
Neural networks for control systems – a survey.
Automatica, 28 (1992), pp. 1083-1112
[Jang, 1993]
J.R. Jang.
ANFIS: Adaptative-networkbased fuzzy inference system.
IEEE Trans. on Systems, Man and Cybernetics, 23 (1993), pp. 665-685
[Jiang, 1994]
J. Jiang.
Design of reconfigurable control systems using eigenstructure assignments.
International Journal of Control, 59 (1994), pp. 395-410
[Jordan et al., 1992]
I. JordanS Michael, Davis E. Rumelhart.
Forward models: Supervised learning with a distal teacher.
Cognitive Science, 16 (1992), pp. 307-354
[Kaminer et al., 1995]
I. Kaminer, A.M. Pascoal, P.P. Khargonekar, E.E. Coleman.
A velocity algorithm for the implementation of gain-scheduled controlle.
Automatica, 31 (1995), pp. 1185-1192
[Linden and Kinndermann, 1989]
A. Linden, J. Kinndermann.
Inversion of multilayer nets.
pp. 425-430
[Looze et al., 1985]
D.P. Looze, J.L. Weiss, J.S. Eterno, N.M. Barret.
An automatic redesign approach for restructurable control systems.
IEEE Control Systems Magazine, 5 (1985), pp. 16-22
[Morari et al., 1989]
Manfred. Morari, Zafirou Evanghelos.
Robust Process Control.
Prentice-Hall, (1989),
[Morse and Ossman, 1990]
W.D. Morse, K.A. Ossman.
Modelfollowing reconfigurable flight control system for the AFTI/F-16.
Journal of Guidance, Control and Dynamics, 13 (1990), pp. 969-976
[Noriega et al., 1998a]
Jose R. Noriega, H. Wang.
A heuristic approach to fault tolerant control of unknown nonlinear systems using neural networks.
Proceedings of Fifth IFAC Workshop rithms and architectures for real-time control, pp. 265-269
[Noriega et al., 1998b]
Jose.R. Noriega, Wang. Hong.
A direct adaptive neural-network control for unknown nonlinear systems and its application.
IEEE Transactions on Neural Networks, 9 (1998), pp. 27-34
[Ochi, 1993]
Y. Ochi.
Application of feedback linearisation method in a digital restructurable flight control system.
Journal of Guidance, Control and Dynamics, 16 (1993), pp. 111-117
[Ogata and Katsuhiko, 1993]
Katsuhiko Ogata.
Ingenierí de Control Moderna.
2ª, Prentice Hall Hispanoamericana S.A, (1993),
[Saludes et al., 2003]
Sergio. Saludes, M.J. Fuente.
Fault tolerant fuzzy IMC control in a pH process.
Proceedings of the European Control Conference,
[Saludes et al., 2005]
Sergio Saludes, M.J. Fuente.
Support vector based novelty detection for fault tolerant control.
Proceedings of the European Control Conference, pp. 5820-5825
[Sánchez et al., 1998]
E. Sánchez, J.M. Gómez, M.J. Cano Izquierdo, Y.A. Araúzo Bravo, J. Dimitriadis, López Coronado.
Adaptive IMC using fuzzy neural networks for the control on non linear systems.
The European Conference on Integration in Manufacturing,
[Wang and Wang, 1999]
H. Wang, Y. Wang.
Neural-networkbased fault-tolerant control of unknown nonlinear systems.
IEE Proceedings-Control Theory and Applications, 146 (1999), pp. 389-398
[Wang et al., 1994]
H. Wang, M. Brown, C.J. Harris.
Fault detection for a class of unknown nonlinear systems via associative memory networks.
IMechE J, I, Syst. Control Eng., 79 (1994), pp. 1415-1441
Este trabajo ha sido Financiado por la Comisión Inter- ministerial de Ciencia y Tecnologí (CICYT) a través del proyecto DPI2006-15716-C02-02
Copyright © 2007. Elsevier España, S.L.. Todos los derechos reservados