Abstract
As it was shown in the last chapters, neural networks are useful tools to solve nonlinear problems concerning the control of dynamic systems. The method of the identification of systems with isolated nonlinearities (chapters 5, 7 and 8) can be used to get information about unknown nonlinearities and non-measurable states of the system (observer function) in a stable manner. For plants like rolling mills, the guarantee of stability in the operating area is an indispensable feature. In this chapter two possible nonlinear problems in rolling mills are described and solved with neural network based identification methods. It can be seen how the extracted knowledge of the nonlinear system is used to get better control results. The problems which are described are the identification of winder eccentricities and the identification of the nonlinear roll bite behaviour. In the last section experimental results are shown.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Aeberli, K.: Japanisches Aluminiumkaltwalzwerk fertigt Dosenbleche höchster Qualität. Engineering and Automation, Vol. 6, 1994, pp. 20–23.
Bryant, G.F.: Automation of Tandem Mills. The Iron and Steel Institute, Carlton House Terrace, London, 1973.
Lenz, IL, Schröder, D.: Local Identification using Artificial Neural Networks. Proceedings of the Ninth Yale Workshop on Adaptive and Learning Systems, Yale , 1996, pp. 83–88.
Martinez, T., Gramckow, O., Protzel, P.: Walzwerksteuerung mit neuronalen Netzen. VDI Berichte No. 1184, 1995, pp. 35–42.
Martinez, T., Gramckow, O., Protzel, P.: Neuronale Netze zur Steuerung von Walzstraßen. atp — Automatisierungstechnische Praxis, Heft 38, 1996, pp. 28–42.
Narendra, K., Annaswamy, A.M.: Stable Adaptive Systems. Prentice Hall, Englewood Cliffs, New Jersey, 1989.
Schaffner, C, Schröder, D.: An Application of General Regression Neural Networks to Nonlinear Adaptive Control. EPE ′93, Brighton, UK. Proceedings, Vol. 4, 1993, pp. 219–223.
Schlang, M.: Neuronale Netze zur Prozessteuerung in der Stahlverarbeitung. VDI Berichte No. 1282, München und Erlangen, 1996.
Schröder, D.: Elektrische Antriebe 2. Springer-Verlag, Berlin, Heidelberg, 1995
Stone, M. D.: Rolling of thin strip. Iron & Stell Eng. 30, Part I, 1953, pp. 61–73.
Straub, S., Schröder, D.: An Example of an Application of Neural Networks in Rolling Mills: Compensation of the Non Circularity of Winders. Proceedings of IFAC 95, Munich, Germany, 1995, pp. 583–590.
Wusatowski, Z.: Grundlagen des Walzens. VEB Deutscher Verlag für Grundstoffindustrie, Leipzig 1963.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Straub, S. (2000). Nonlinear Observer Structures for the Identification of Isolated Nonlinearities in Rolling Mills. In: Schröder, D. (eds) Intelligent Observer and Control Design for Nonlinear Systems. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-04117-8_9
Download citation
DOI: https://doi.org/10.1007/978-3-662-04117-8_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-08346-4
Online ISBN: 978-3-662-04117-8
eBook Packages: Springer Book Archive