Abstract
An architecture to perform a neural controller during its operation based upon indirect learning model is proposed in this paper, and a new vision of this model introducing a supervisory level is discussed. A supervisory level is used to monitorize the performance of a neural controller composed of a multilayer adaptive network of nonlinear elements, which can be taught to control the time responses of a non-linear system subjected to changes during its operation. The role of the supervisory level is examined throught an explanatory simulation process.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
S.Y. Kung and J.N. Hwang, "Neural Networks Architectures for Robotic Applications," IEEE Trans. Robotics Automat., Vol 5, No 5, pp 641–657, Oct. 1989.
E. Grant and B. Zhang, "A Neural-Net Approach to Supervised Learning of Pole Balancing," in Proc. IEEE Int. Symp. on Intelligent Control, pp 123–128, 1988.
K. M. Passino, M. A. Sartoris and P.J. Antsaklis, "Neural Computing for Numeric-To-Symbolic Conversion in Control Systems," IEEE Contr. Syst. Mag., Vol 9, No 3, pp 44–52, April 1989.
S. Lane, D. Handelman and J. Gelfand, "A Neural Network Computational Approach to Reflexive Motor Control," in Proc. IEEE Int. Symp. on Intelligent Control, 1988.
S.P. De Weerth, L. Nielsen, C.A. Mead and K.J. Astrom, "A Simple Neuron Servo," IEEE Trans. on Neural Network, Vol 2, No 2, March 1991.
P. Antsaklis, "Neural Networks in Control Systems," IEEE Contr. Syst. Mag., Vol 10, No 3, pp 3–5, April 1990.
Wittenmark B, Astrom K. J. (1984): "Practical Issues in the Implementation of Self-Tuning Control". Automatica, Vol 20, pp 595–605.
Landau. I.D. (1979): "Adaptive Control-The Model Reference Approach". Marcel Dekker, New York.
Isermann R. Lachmann K.H. (1985): "Parameter-adaptive Control with Configurations Aids and Supervision Functions". Automatica, Vol 21, No 6 pp 625–638.
Martinez M.A. (1991): "Indicadores para la Supervision del Control Adaptativo. Implementación mediante metodología de Sistema Experto". Doctoral Dissertation. DISCA. Univ. Politecnica Valencia, Valencia, Spain.
L. Gordon Kraft and D.P. Campagna, "A Comparison Between CMAC Neural Network Control and Two Traditional Adaptive Control Systems," IEEE Contr. Syst. Mag., Vol 10, No 3, pp 36–43, April 1990.
M. Sarens, A. Souquet, M. Renders and H. Bersini, "Preliminary Comparisons Between A Neural Adaptive Controller and a Model Reference Adaptive Controller" The International Neural Network Conference, Paris, 1990.
D. Psaltis, A. Sideris and A.A. Yamamura, "A Multilayered Neural Network Controller," IEEE IEEE Contr. Syst. Mag., April 1988.
B. Widrow and R. Winter: "Neural Nets for Adaptive Filtering and Adaptive Pattern Recognition". Computer. March 1988.
Widrow, B.(1986). "Adaptive inverse control," Second IFAC Workshop ain Adaptive Systems in Control and Signal Processing Sweden.
D.E. Rumelhart, G.E. Hinton and R.J. Williams, "Learning Internal Representations by Error Propagation", in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol1: Foundations,D.E. Rumelhart and J.L. McClelland, eds. Cambridge, MA: MIT Press, 1986.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
García-Padilla, F., Morant-Anglada, F. (1991). A supervisory technique to apply neural networks in control. In: Prieto, A. (eds) Artificial Neural Networks. IWANN 1991. Lecture Notes in Computer Science, vol 540. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0035925
Download citation
DOI: https://doi.org/10.1007/BFb0035925
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54537-8
Online ISBN: 978-3-540-38460-1
eBook Packages: Springer Book Archive