Abstract
In this paper it is investigated whether neural networks are able to improve the performance of a PI controller when controlling a combustion engine. The idea is not to replace but to assist a PI controller by a neural co-controller. Three different neural approaches are investigated for this use: Dynamic RBF (DRBF), Adaptive Time-Delay Neural Network (ATNN), and Local Ellipsoidal Model Network (LEMON).
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.
References
M. Ayoubi. Das dynamische Perzeptronmodell zur experimentellen Modellbildung nichtlinearer Prozesse. Informatik Forschung und Entwicklung, 12:14–22, 1997.
M. Ayoubi and R. Isermann. Radial Basis Function Networks with Distributed Dynamics for Nonlinear Dynamic System Identification. In Third European Congress on Intelligent Techniques and Soft Computing (EUFIT), 1995.
Walter L. Baker and Jay A. Farrell. An introduction to connectionist learning control systems. In David A. White and Donald A. Sofge, editors, Handbook of Intelligent Control, chapter I, pages 35–63. VAN NOSTRAND REINHOLD, New York, 1992.
S. Chen, S. Billings, and P. Grant. Nonlinear System Identification using Neural Networks. Int. J. Control, 51(6), 1990.
Roderick Murray-Smith, editor. Multiple model approaches to modelling and control. Taylor & Francis, London, 1997.
K.S. Narendra, S. Kumpati, and K. Parthasarathy. Identification and Control of Dynamical Systems Using Neural Networks. IEEE Trans. Neural Networks, 1(1):4–27, 1990.
Martin Riedmiller and Heinrich Braun. A direct adaptive method for faster back-propagation learning: The rprop algorithm. In Proceedings of the IEEE International Conference on Neural Networks 1993 (ICNN 93), 1993.
M. Sturm and K. Eder. Self-organizing process state detection for on-line adaptation tasks. In A. B. Bulsari, S. Kallio, and D. Tsaptsinos, editors, Solving Engineering Problems with Neural Networks, Proceedings of the International Conference EANN’ 96, pages 33–36, London, 6 1996. Systeemitekniikan seura ry.
Michael Sturm and Till Brychcy. On-Line Prozeßraumkartierung mit ellipsoider Vektorquantisierung zur lokalen Modellbildung. In A. Grauel/ W. Becker/ F. Belli, editor, Fuzzy-Neuro-Systeme’ 97-Computational Intelligence, Proceedings in Artificial Intelligence, pages 463–470. Infix Verlag, St. Augustin, 1997.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ungerer, C., Stübener, D., Kirchmair, C., Sturm, M. (1999). Supporting Traditional Controllers of Combustion Engines by Means of Neural Networks. In: Reusch, B. (eds) Computational Intelligence. Fuzzy Days 1999. Lecture Notes in Computer Science, vol 1625. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48774-3_16
Download citation
DOI: https://doi.org/10.1007/3-540-48774-3_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66050-7
Online ISBN: 978-3-540-48774-6
eBook Packages: Springer Book Archive