This content is not included in your SAE MOBILUS subscription, or you are not logged in.
HiL-Calibration of SI Engine Cold Start and Warm-Up Using Neural Real-Time Model
ISSN: 0148-7191, e-ISSN: 2688-3627
Published March 08, 2004 by SAE International in United States
Annotation ability available
The modern engine design process is characterized by shorter development cycles and a reduced number of prototypes. However, simultaneously exhaust after-treatment and emission testing is becoming increasingly more sophisticated. The introduction of predictive real-time simulation tools that represent the entire powertrain can likely contribute to improving the efficiency of the calibration process.
Engine models, which are purely based on physical first principles, are usually not capable of real-time applications, especially if the simulation is focused on cold start and warm-up behavior. However, the initial data definition for the ECU using a Hardware-in-the-Loop (HiL)-Simulator requires a model with both real-time capability and sufficient accuracy. The use of artificial intelligence systems becomes necessary, e.g. neural networks.
Methods, structures and the realization of a hybrid real-time model are presented in this paper, which combines physical and neural network models. Neural networks can predict the response of a real physical system to varying input conditions after they have been subjected to an adequate training procedure. Such a network, in combination with physical a priori information embedded in the model structure provides for excellent generalization capability. This takes the form of an appropriate reaction to previously unavailable data. In addition, this enables the model to describe and simulate the behavior of a SI engine under transient and nonlinear conditions.
This document describes the approach and its verification of a reference engine under cold start and warm-up conditions.
- 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
- Stefan Pischinger - Institute for Internal Combustion Engines (VKA), RWTH Aachen
- Christof Schernus - FEV Motorentechnik GmbH, Aachen
- Georg Lütkemeyer - FEV Motorentechnik GmbH, Aachen
CitationWinsel, T., Ayeb, M., Theuerkauf, H., Pischinger, S. et al., "HiL-Calibration of SI Engine Cold Start and Warm-Up Using Neural Real-Time Model," SAE Technical Paper 2004-01-1362, 2004, https://doi.org/10.4271/2004-01-1362.
- Aquino, C.F. Transient A/F Control Characteristics of the 5 Liter Central Fuel Injection Engine SAE-Paper No. 810494 1981
- Ayeb, M. Lichtenthäler, D. Winsel, T. Theuerkauf, H.J. SI Engine Modeling Using Neural Networks SAE-No. 980790 Detroit 1998
- CARTS ® - Computer Aided Realtime Testsystem, Manual / Operating Instructions carts Real-Time Solutions GmbH Kassel 2003
- GT-POWER - User Manual and Tutorial, GT-SUITE ™ Version 5.2 Gamma Technologies, Inc. Westmond 2001
- Hagan, M.T. Menjaj, M.B. Training Feedforward Networks with the Marquardt Algorithm IEEE-Transactions on Neural Networks 5 6 November 1994
- Marquardt, D. An Algorithm for Least Squares Estimation of Non-Linear Parameters J.Soc. Ind. Appl. Math. 1963
- Morel, T. Wahiduzzaman, S. Effect of Manifold Wall Wetting and Fuel Evaporation on Transient Engine Operation Graz 2001
- Moskwa, J. J. Automotive Engine Modeling Real Time Control Massachusetts Institute of Technology USA 1988
- Narendra, K.S. Parthasarathy, K. Identification and Control of Dynamical Systems Using Neural Networks IEEE-Transactions on Neural Networks 1 1 March 1990
- Onder, C.-H. Zürich 1993
- Pischinger, S Theuerkauf, H. J. Ayeb, M. Lütkemeyer, G. Schernus, C. Winsel, T. Wilhelm, C. Nürnberg 2002
- Pischinger, S. Schernus, C. Lütkemeyer, G. Winsel, T. Theuerkauf, H. J. Ayeb, M. Aachen 2003
- Schernus, C. Rauscher, M. Fieweger, K. Lang, O. Transient Simulation of a Diesel Engine as a Tool for Virtual Calibration, GT-Suite Users Conferences Frankfurt, Dearborn, Yokohama 1999
- 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
- Silvestri, J. Morel, T. Lang, O. Schernus, C. Rauscher M. Aachen 2000
- Winsel, T. Ayeb, M. Lichtenthäler, D. Theuerkauf, H.J. A Neural Estimator for Cylinder Pressure and Engine Torque, SAE International Congress , SAE Nr. 1999-01-1165 Detroit (USA) 1999
- Winsel, T. X tra NN Software-Tools zur Generierung extrapolationsfähiger Prozessmodelle mit neuronalen Netzen IEE-AT, Universität Kassel 1999-2003
- Winsel, Th. Stabile neuronale Prozessmodelle: Automatisierte Generierung echtzeitfähiger Modelle zur Nachbildung des dynamischen Verhaltens von Verbrennungsmotoren VDI-Verlag Düsseldorf 2002