This content is not included in your SAE MOBILUS subscription, or you are not logged in.
A Neural Estimator for Cylinder Pressure and Engine Torque
Technical Paper
1999-01-1165
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
The paper presents a new method based on neural networks to model the dynamic behavior of combustion pressure in SI engine cylinders, represented only by conventional input-output data. The approach is based on a functional representation of the pressure curve. The function parameters are adjusted by training a static neural network (SNN) for each working cycle. These parameters resp. “weights” are used in the following as reference pressure feature sequences. The sequences are simulated using time delay neural network (TDNN) as functions of engine speed, manifold pressure, ignition time and A/F ratio. The developed models can be used as stand alone models or as submodels within a global structure. It can be integrated as a real-time model in a HIL simulator to stimulate an ECU or implemented within an ECU for torque estimation. Performance of the proposed modeling strategy is verified by comparing experimental data from a test bench to real-time simulation results.
Recommended Content
Authors
Topic
Citation
Winsel, T., Ayeb, M., Lichtenthäler, D., and Theuerkauf, H., "A Neural Estimator for Cylinder Pressure and Engine Torque," SAE Technical Paper 1999-01-1165, 1999, https://doi.org/10.4271/1999-01-1165.Also In
Electronic Engine Controls 1999: Neural Networks, Diagnostic and Electronic Hardware, and Controls
Number: SP-1419 ; Published: 1999-03-01
Number: SP-1419 ; Published: 1999-03-01
References
- Ayeb, M., Lichtenthäler, D., Winsel, T., Theuerkauf, H.J.: SI Engine Modeling Using Neural Networks, SAE-No. 980790, Detroit, 1998
- Hagan, M.T., Menjaj, M.B.: Training Feedforward Networks with the Marquardt Algorithm, IEEE-Transactions on Neural Networks, Vol. 5, No. 6, November 1994
- Kuratle, R.: Meßzündkerzen mit integriertem Drucksensor, MTZ - Motortechnische Zeitschrift 55, Germany, 1994
- Leonhardt, S., Schwarz, R., Isermann, R.: Real-Time Supervision of the Diesel Engine Injection Process, SAE-No. 970535, Detroit, 1997
- Marquardt, D.: An Algorithm for Least Squares Estimation of Non-Linear Parameters, J.Soc. Ind. Appl. Math., 1963
- Narendra, K.S., Parthasarathy, K.: Identification and Control of Dynamical Systems Using Neural Networks, IEEE-Transactions on Neural Networks, Vol. 1, No. 1, March 1990
- Nguyen, D., Widrow, B.: Improving the Learning Speed of 2-Layer Neural Networks by Choosing Initial Values of the Adaptive Weights, International Joint Conference of Neural Networks, Vol. 3, No. 6, July 1990
- Woermann, R. J., Klages, B., Theuerkauf, H.J.: CARTS - A Hardware in the Loop Simulator for Test and Development of Automotive Control Units, SAE-No.961019, Detroit, 1996
- Woermann, R. J., Klages, B., Theuerkauf, H.J.: A High Resolution Real-Time Model of a Diesel Engine, SAE-No.970614, Detroit, 1997