Databased modeling: An AI Toolchain for the development process of combustion engines
2022-01-0188
03/29/2022
- Event
- Content
- Predictive physical modeling is an established method used in the development process for any automotive component or system. While accurate predictions can be issued after tuning model parameters, long computation times can be expected depending on the complexity of the model at hand. As the requirements of the components/systems to be developed continuously increase, new optimization approaches are constantly being applied to solve multidimensional objectives and resulting conflicts optimally. Unfortunately, some of those approaches are deemed not feasible, as the computational times of the required single predictions using conventional simulation models are too high. Therefore, it is proposed to use data-based models such as trained neural networks instead of physical models to address this issue. Previous efforts have failed due to a weak database and the resulting poor predictive ability of data-based models. This paper introduces an AI Toolchain used for data-based modeling of combustion engine components. As stated, the underlying dataset provides the basis for the successful training of accurate neural networks. Consequently, 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 intended prediction variables. Second, datasets will be post-processed according to evaluation findings. Eventually, the layout and training of neural networks predicting combustion characteristics, e.g. MFB turnover rates, pressure quantities and NO-emissions, and motor components, e.g. compressor, catalyst, 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-based engine model. This work represents the current status concerning this effort.
- Citation
- Milojević, S., Rether, D., Bodza, S., Grill, M. et al., "Databased modeling: An AI Toolchain for the development process of combustion engines," SAE Technical Paper 2022-01-0188, 2022, .