Abstract
This study allows comparing two competitive modelling techniques to identify the electric arc dynamics of a furnace. The first technique relies on a linear kRX model whereas the second one relies on a non linear ARX model built from a MLP neural network. Results clearly point out the benefits of using a non-linear model for this particular non-linear application.
Preview
Unable to display preview. Download preview PDF.
References
A.S Hauksdottir, T. Söderström, Y.P Thorfinnson, and A. Gestsson. System Identification of a Three-Phase Submerged-Arc Ferrosilicim Furnace. In IEEE Transactions on Control System Technology, number 4, pages 377–387, December 1995.
P.E King, T.L Ochs, and A.D Hartman. Chaotic Responses in Electric Arc Furnaces. In Journal of Applied Physics, number 4, pages 2059–2065, August 1994.
L. Ljung. System Identification: Theory for the User. P.T.R Prentice Hall, 1987.
C. Ledoux. Application des techniques conneaionnistes á l'identification de systémes dynamiques. PhD thesis, Université Pierre et Marie Curie, Paris, France, Mars 1997.
J. Sjöberg, Q. Zhang, A. Benveniste, B. Deylon, P.Y Glorennec, H. Hjalmarsson, and A. Juditsky. Nonlinear Black-Box Modeling in System Identification: a Unified Overview. Automatica. 31. 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ledoux, C., Bonnard, F. (1997). Identification of the electric arc of a furnace. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020259
Download citation
DOI: https://doi.org/10.1007/BFb0020259
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive