In-cylinder pressure-based convolutional neural network for real-time estimation of low-pressure cooled exhaust gas recirculation in turbocharged gasoline direct injection engines

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.

Development of an experimental test bench and a psychrometric model for assessing condensation on a low-pressure exhaust gas recirculation cooler

“…In first place, Figure 9 shows the tests with different EGR temperature at an MFR of 20 kg/h and at an initial coolant temperature of 5°C. As can be seen, three notable stages are outstanding in the figure: on one hand, in the first stage (Stage 1), the condensates start and the difference between the test and the model prediction is maximum; in the second stage (Stage 2), the measured and the modeled condensation rates are similar, decreasing due to the increasing coolant temperature, and end when the theoretical condensation stops (t dew from equation (11)). On the other hand, the third stage (Stage 3) ends when the actual condensation is stopped.…”

“…Regarding t dew in which the production of condensates stops, as it is mentioned in equation (11), notable differences are observed between MFRs, coolant temperatures and EGR temperatures. In Figure 14, the time until the condensation stops is shown for all MFRs and initial coolant temperature at an EGR temperature of 90°C.…”

“…10 In-cylinder control system functioning is based on the reduction of pollutants within the source, for example, controlling the injection scheme (pressure, duration, etc.) using exhaust gas recirculation (EGR) 11 or injecting water into the cylinders. 12,13 This work is focused on using EGR as an emission-reduction technique.…”