This content is not included in your SAE MOBILUS subscription, or you are not logged in.
STEPS TOWARDS AN OPTIMIZATION OF THE DYNAMIC EMISSION BEHAVIOR OF IC ENGINES: Measurement Strategies - Modeling - Model Based Optimization
ISSN: 0148-7191, e-ISSN: 2688-3627
Published December 01, 2001 by SAE International in United States
Annotation ability available
New technologies have been applied to IC engines in order to fulfill rising demands concerning consumption, drivability and emissions. These additional technologies result in a high amount of process inputs that are controlled by the Electronic Control Unit (ECU). Thus, the task of finding optimum settings for all variables becomes more and more complex. In this contribution, model-based approaches are presented which help finding optimal engine control setting maps. The optimization itself bases on fast neural networks. The quality of these nets decisively depends on good measurement data. Therefore, a new advanced measurement strategy will be presented which was designed to dynamically cover the whole area of interest where the engine is run.
Despite an optimum stationary engine performance unfavorable combustion conditions are likely to occur during transient conditions leading to dynamic emission peaks. To compensate for that, predictive control functions are proposed and their parameters are determined by model-based optimization routines.
|Optimizing Internal Combustion Engine Performance Through Response Surface Methodology
|Real-time Pedestrian Detection using Convolutional Neural Network on Embedded Platform
CitationHafner, M., "STEPS TOWARDS AN OPTIMIZATION OF THE DYNAMIC EMISSION BEHAVIOR OF IC ENGINES: Measurement Strategies - Modeling - Model Based Optimization," SAE Technical Paper 2001-01-1793, 2001, https://doi.org/10.4271/2001-01-1793.
- Schüler, M. Hafner, M. Isermann, R. Model-based Optimization of IC Engines by Means of Fast neural Networks MTZ Worldwide 61 10 11 2000
- Röpke, K. Waschatz, U. Steigerung der Effizienz in der Motorapplikation durch statistische Versuchsplanung Tagungsband 2. Symposium für den Antriebsstrang von Kraftfahrzeugen 1999 145 155
- Isermann, R. Identifikation dynamischer Systeme Berlin Springer 1992
- Pitsch, H. Barths, H. Peters, N. Three-dimensional Modeling of NOx and Soot Formation in DI-Diesel Engine Using Detailed Chemistry Based on a Flamelet Approach SAE International Congress Detroit, USA 1996
- Nelles, O. Nonlinear System Identification with Local Linear Neuro-Fuzzy Models Darmstadt Technische Universität 1999
- Ayoubi, M. Nonlinear System Identification Based on Neural Networks with Locally Distributed Dynamics and Application to Technical Processes Darmstadt Technische Universität 1996
- Takagi, T. Sugeno, M. Fuzzy Identification of Systems and its Applications to Modeling and Control IEEE Transactions on Systems, Man and Cybernetics 15 116 132 1985
- Hafner, M. Model Based Determination of Dynamic Engine Control Function Parameters SAE Spring Fuels & Lubricants Meeting Orlando, USA 2001
- Hafner, M. Schüler, M. Nelles, O. Isermann, R. Fast Neural Networks for Diesel Engine Control Design Control Engineering Practice (CEP) 8 11 2000
- Hafner, M. Isermann, R. The Use of Stationary and Dynamic Emission Models for an Improved Engine Performance in Legal Test Cycles International Workshop on Modeling, Emissions and Control in Automotive Engines Salerno, Italy 2001