This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
A Combined Physical / Neural Approach for Real-Time Models of Losses in Combustion Engines
Technical Paper
2007-01-1345
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
Reliable estimation of pumping and friction losses in modern combustion engines allows better control strategies aiming at optimal fuel consumption and emissions. Sophisticated simulation tools enable detailed simulation of losses based as well on physical and thermodynamic laws as well as on design data. Models embedded in these tools however are not real-time capable and cannot be implemented into the programs of the electronic control units (ECU's).
In this paper an approach is presented that estimates the pumping and friction losses of a combustion engine with variable valve train (VVT). Particularly the pumping losses strongly depend on the control of variable valve train by ECU.
The model is based on a combination of a globally physical structure embedding data driven sub models based on test bed measurements. Losses are separated concerning different component groups (bearings, pistons, etc.). Modularity of the model allows a simple parameterization for different engines of the same family. Additionally design data, available from the development process, are included to reduce measuring and to enhance the scalability of the model.
These models are real-time capable and can be integrated as well in HiL test systems as in ECU's to optimize fuel injection and VVT control strategies.
Recommended Content
Authors
- Christian Wilhelm - Institute of Electrical Power Engineering - Drive Engineering (IEE-AT), University of Kassel
- Thomas Winsel - Institute of Electrical Power Engineering - Drive Engineering (IEE-AT), University of Kassel
- Mohamed Ayeb - Institute of Electrical Power Engineering - Drive Engineering (IEE-AT), University of Kassel
- Heinz J. Theuerkauf - Institute of Electrical Power Engineering - Drive Engineering (IEE-AT), University of Kassel
- Sven Brandt - Institute of Machine Design and Tribology (IMK), University of Kassel
- Elmar Busche - Institute of Machine Design and Tribology (IMK), University of Kassel
- Claudio Longo - Institute of Machine Design and Tribology (IMK), University of Kassel
- Gunter D. Knoll - Institute of Machine Design and Tribology (IMK), University of Kassel
Citation
Wilhelm, C., Winsel, T., Ayeb, M., Theuerkauf, H. et al., "A Combined Physical / Neural Approach for Real-Time Models of Losses in Combustion Engines," SAE Technical Paper 2007-01-1345, 2007, https://doi.org/10.4271/2007-01-1345.Also In
References
- Ayeb, M. Zur modellbasierten Reglung technischer Prozesse mit dynamischen neuronalen Netzen Shaker-Verlag Aachen 1998
- CARTS ® - Computer Aided Real-time Testsystem Handbuch / Bedienungsanleitung carts Real-Time Solutions GmbH Kassel 2005 http://www.carts.de
- Cybenko, G. Approximations by Superpositions of a Sigmoidal Function Mathematics of Control, Signals and Systems 2 183 192 1989
- Hagan, M. T. Menjaj, M. B. Training Feedforward Networks with the Marquardt Algorithm IEEE-Transaction on Neural Networks 5 1994 6
- Hornik, K. Stinchcombe, M. White, H. Multilayer Feedforward Networks are Universal Approximators Neural Networks 2 359 366 1989
- Lechtape-Grüter, R. Kolbenringdynamik RWTH Aachen 1994 3-88122-815-2
- Marquardt, D.W. An Algorithm for Least-Squares Estimation of Nonlinear Parameters J. Soc. Indust. Math. 11 2 431 441 June 1963
- Patterson, D. Künstliche neuronale Netze Prentice Hall Auflage 1996
- Pischinger, S Theuerkauf, H. J. Ayeb, M. Lütkemeyer, G. Schernus, C. Winsel, T. Wilhelm, C. Erforschung eines Motormodells zur Applikationshilfe am Beispiel des Kaltstart- und Warmlaufverhaltens 2002 Nürnberg 2002
- Schernus, C. Pischinger, S. Lütkemeyer, G. Theuerkauf, H. J. Winsel, T. Investigation of Predictive Models for Application of Engine Cold-Start Behavior SAE-No. 2004-01-0994 Detroit 2004
- Schönen, R. Strukturdynamische Mehrkörper-Simulation des Verbrennungsmotors mit elastohydro-dynamischer Grundlagerkopplung Univ. Kassel 2001 3-89958-507-0
- Stöcker, H. Taschenbuch mathematischer Formeln und moderner Verfahren Harry Deutsch Auflage 1999
- Wilhelm, C. Theuerkauf, H. Schernus, C. Winsel, T. Ayeb, M. Schleppmomentmodellierung mit kombinierten physikalisch / neuronalen Prozessmodellen für Kalt- und Warmlauf Berlin 2005 3-8169-2491-3
- Wilhelm, K. Strukturdynamische Analyse von Kurbelwelle und Motorblick mit elastohydrodynamischer Wechselwirkung RWTH Aachen 1998 3-88122-861-6
- Winsel, T. XtraNN - Software-Tools zur Generierung extrapolationsfähiger Prozessmodelle mit neuronalen Netzen Universität Kassel 1999-2003
- Winsel, T. Stabile neuronale Prozessmodelle: Automatisierte Generierung echtzeitfähiger Modelle zur Nachbildung des dynamischen Verhaltens von Verbrennungsmotoren VDI-Verlag Düsseldorf 2002
- Winsel, T. Ayeb, M. Wilhelm, C. Theuerkauf, H. J. Pischinger, S. Woermann, R. Schernus, C. HiL-based ECU-Calibration of SI Engine with Advanced Camshaft Variability SAE-No. 2006-01-0613 Detroit 2006