The Virtual Boosted DISI Engine Model Development Based on Artificial Neural Networks
2022-01-0456
03/29/2022
- Event
- Content
- To efficiently reduce the required experimental data and improve the prediction accuracy, a virtual engine mod-el has been built by integrating an artificial neural network (ANN) system consisting of multiple subnets with the principle component analysis (PCA) method. The PCA method could preprocess the training data and leads to a more efficient training process. By coupling with 1-D GT power platform, this model has been adopted to predict the combustion phases (including CA10, CA50 and CA90), exhaust gas temperature, brake specific fuel consumption rate (be) and engine emissions such as un-burnt hydrocarbon (UBHC), NOx and CO. The results are then compared with the experimental data from around 5000 operating points of a boosted DISI engine running at universal performance map and conditions with various valve timing configurations. The mean abso-lute errors in combustion phases and exhausted gas temperature are less than 1.0 °CA and 10.1 K, respectively. The average relative errors in be , UBHC, NOx and CO are close to 1.5%, 4.67%, 5.49% and 5.84%, respective-ly. Furthermore, the predicted results and experimental data show satisfying similar trends in terms of the CA50 and CA10-CA90 under different crank speed and brake specific fuel consumption rate under different VVT con-figurations. With a 2.2GHz single-core processor, the turnover time for one single engine cycle calculation using the virtual engine model is less than one-tenth of the real wall time. This illustrates the potential of the proposed model for hardware in the loop (HiL) system and the virtual real drive emission (RDE) development.
- Citation
- Chen, C., Wu, J., Wei, J., and Xu, H., "The Virtual Boosted DISI Engine Model Development Based on Artificial Neural Networks," SAE Technical Paper 2022-01-0456, 2022, .