This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Data-Driven Modeling: An AI Toolchain for the Powertrain Development Process
Technical Paper
2022-01-0158
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
Predictive physical modeling is an established method used in the development process for automotive components and systems. While accurate predictions can be issued after tuning model parameters, long computation times are expected depending on the complexity of the model. As requirements for components and systems continuously increase, new optimization approaches are constantly being applied to solve multidimensional objectives and resulting conflicts optimally. Some of those approaches are deemed not feasible, as the computational times for required single predictions using conventional simulation models are too high. To address this issue it is proposed to use data-driven model such as neural networks. Previous efforts have failed due to sparse data sets and resulting poor predictive ability. This paper introduces an AI Toolchain used for data-driven modeling of combustion engine components. Two methods for generating scalable and fully variable datasets will be shown. Prior to the actual training of neural networks, resulting data is evaluated regarding the distribution of variation parameters in a multidimensional space and the distribution density of prediction variables. Second, datasets will be post-processed according to evaluation findings. Eventually, layout and training of neural networks predicting combustion characteristics, e.g. MFB (Mass Fraction Burned) and pressure quantities, are described. A final summary will conclude the statistical accuracy of corresponding neural networks. Finally, the potential use of neural networks in the development process of internal combustion engines is discussed. The ultimate goal of the research project is the holistic realization of a data-driven engine model. This work represents the current status concerning this effort.
Authors
Topic
Citation
Milojevi, S., Bodza, S., Cimniak, V., Angerbauer, M. et al., "Data-Driven Modeling: An AI Toolchain for the Powertrain Development Process," SAE Technical Paper 2022-01-0158, 2022, https://doi.org/10.4271/2022-01-0158.Also In
References
- Rether , D. , Cimniak , V. , Bodza , S. , Grill , M. et al. A New Class of AI-Based Engine Models 8th International Engine Congress Baden-Baden
- Rether , D. , Cimniak , V. , Grill , M. , and Bargende , M. Nutzung neuronaler Netzwerke zur Virtualisierung am Beispiel von Brennraumvorgängen Experten-Forum 2020 Hanau
- Milojevic , S. , Bodza , S. , Rether , D. , Grill , M. , et al. Next Generation Data-Based Models powered by AI 9th International Symposium on Development Methodology
- Grill , M. and Bargende , M. Das Zylindermodul Neue Simulation nicht nur für zukünftige Brennverfahren MTZ Motortech Z 70 10 2009 778 785 10.1007/BF03252423
- Hann , S. , Grill , M. , and Bargende , M. Laminare Flammengeschwindigkeit - Abmagerung und Hochlast-Abgasrückführung in der Motorsimulation MTZ 79 28 35
- Hann , S. , Palaveev , S. , Grill , M. , Veltman , M. et al. Predicting the Influence of Charge Air Temperature Reduction on Engine Efficiency, CCV and NO x -Emissions of a Large Gas Engine Using a SI Burn Rate Model SAE Technical Paper Series SAE International 400 Commonwealth Drive Warrendale, PA, United States 2020
- Rether , D. , Grill , M. , Schmid , A. , and Bargende , M. Quasi-Dimensional Modeling of CI-Combustion with Multiple Pilot- and Post Injections SAE Int. J. Engines 3 1 2010 12 27 10.4271/2010-01-0150
- Schmid , A. 2011
- Übler , J. and Groeneveld , K. 2019
- Wenig , M. 2013
- Fandakov , A. 2018
- Bossung , C. 2017
- Hochreiter , S. and Schmidhuber , J. Long Short-Term Memory Neural Computation 9 8 1997 1735 1780 10.1162/neco.1997.9.8.1735
- Cho , K. , van Merrienboer , B. , Bahdanau , D. , and Bengio , Y. On the Properties of Neural Machine Translation: Encoder-Decoder Approaches Paper, Cornell University Ithaca, New York, United States of America 2014
- Kingma , D.P. and Ba , J. 2014
- Rumelhart , D.E. , Hinton , G.E. , and Williams , R.J. Learning Internal Representations by Error Propagation Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Volume 1: Foundations Cambridge, MA MIT Press 1986
- Pang , W. https://venturebeat.com/2020/12/16/the-future-of-ai-deployments-reaching-production-is-bright-in-2021/
- Blockwitz , T. , Otter , M. , Akesson , J. , Arnold , M. et al. Functional Mockup Interface 2.0: The Standard for Tool independent Exchange of Simulation Models Proceedings of the 9th International MODELICA Conference, September 3-5, 2012, Munich, Germany, Linköping Electronic Conference Proceedings, 9th International MODELICA Conference Munich, Germany Sept. 3-5, 2012 Linköping University Electronic Press 173 184 2012