No abstract

No abstract

Low-pressure cooled exhaust gas recirculation is one of the most promising technologies for improving fuel efficiency of turbocharged gasoline direct injection engines. To realize the beneficial effects of the low-pressure cooled exhaust gas recirculation, the accurate estimation of the low-pressure cooled exhaust gas recirculation rate is essential for precise low-pressure cooled exhaust gas recirculation control. In this respect, previous studies have suggested in-cylinder pressure-based low-pressure cooled exhaust gas recirculation models to obtain the low-pressure cooled exhaust gas recirculation rate into the cylinders with fast response. However, these methods require considerable manual process of feature engineering to extract and analyze the combustion characteristics from the cylinder pressure traces. Furthermore, the performance of the entire model is limited solely to certain hand-crafted characteristics and their mathematical formulations. To resolve these limitations, we propose an in-cylinder pressure-based convolutional neural network for low-pressure cooled exhaust gas recirculation estimation. Because the convolutional neural network model automatically learns the complex function between the raw input of the high-dimensional cylinder pressure traces and the low-pressure cooled exhaust gas recirculation rate through an end-to-end deep learning framework, this convolutional neural network model provides a more effective and precise modeling process compared to the conventional combustion characteristics-based regression models. The proposed convolutional neural network model consists of the input layer with the previous consecutive cycles of the pressure traces to resolve the model uncertainty from cycle-to-cycle variations. This input layer is connected to one convolutional layer, two fully connected layers, and the final output layer that is the target low-pressure cooled exhaust gas recirculation rate. The proposed model was trained, validated, and tested using a total of 50,000 cycles of engine experimental data under various transient driving conditions. The remarkable accuracy of the proposed model was evaluated with R2 values over 0.99 and root mean square error values of less than 1.5% under the transient conditions. Moreover, the real-time performance and low memory requirement were also verified on the target embedded platform.

Low pressure cooled exhaust gas recirculation (LP-EGR) system has been widely adopted to improve energy efficiency in turbocharged gasoline direct injection (GDI) engines. In order to utilize complete beneficial effects of the LP-EGR, a technique capable of accurately observing the LP-EGR flow into the cylinder in real-time is a prerequisite. To precisely estimate the LP-EGR rate in real-time, this paper proposes artificial neural network (ANN) models and its implementation on a real-time embedded system. As inputs for the ANN models, 12 combustion parameters physically correlated with the LP-EGR in the combustion process are selected and calculated from the in-cylinder pressure. The ANN models for the real-time LP-EGR estimation were trained with the steady-state data of 30,000 cycles and their hyper-parameters were searched by a hyper-parameter optimization method. Moreover, a model-based design procedure is introduced to implement the optimized ANN models on the real-time embedded system. Since the proposed implementation performs the validation procedure for each process, it provides a systematic and seamless process for creating ANN models for real-time embedded systems. In real-time experiments under eight steady-state engine operating points, the embedded ANN models show the estimation performance with R2 of above 0.9716. The operation time of each ANN was less than 1.285 ms meaning that the target system can operate in real-time sufficiently with a mass-produced 32 bit microprocessor up to 256 MHz.