No abstract

With global warming, and internal combustion engine emissions as the main global non-industrial emissions, how to further optimize the power performance and emissions of internal combustion engines (ICEs) has become a top priority. Since the internal combustion engine is a complex nonlinear system, it is often difficult to optimize engine performance from a certain factor of the internal combustion engine, and the various parameters of the internal combustion engine are coupled with each other and affect each other. Moreover, traditional experimental methods including 3D simulation or bench testing are very time consuming or expensive, which largely affects the development of engines and the speed of product updates. Machine learning algorithms are currently receiving a lot of attention in various fields, including the internal combustion engine field. In this study, an artificial neural network (ANN) model was built to predict three types of indicators (power, emissions, and combustion phasing) together, including 50% combustion crank angle (CA50), carbon monoxide (CO), unburned hydrocarbons (UHC), nitrogen oxides (NOx), indicated mean effective pressure (IMEP), and indicated thermal efficiency (ITE). The goal of this work was to verify that only one machine learning model can combine power, emissions, and phase metrics together for prediction. The predicted results showed that all coefficients of determination (R2) were larger than 0.97 with a relatively small RMSE, indicating that it is possible to build a predictive model with three types of parameters (power, emissions, phase) as outputs based on only one ANN model. Most importantly, when optimizing the powertrain control strategy of a hybrid vehicle, only a surrogate model can help establish the relationship between the input and output parameters of the whole engine, which is the need of the future research. Overall, this study demonstrated that it is feasible to integrate three types of combustion-related parameters in a single machine learning model.

Engine development needs to reduce costs and time. As the current main development methods, 1D simulation has the limitations of low accuracy, and 3D simulation is a long, time-consuming task. Therefore, this study aims to verify the applicability of the machine learning (ML) method in the prediction of engine efficiency and emission performance. The support vector regression (SVR) algorithm was chosen for this paper. By the selection of kernel functions and hyperparameters sets, the relationship between the operation parameters of a spark-ignition (SI) engine and its economic and emissions characteristics was established. The trained SVR algorithm can predict fuel consumption rate, unburned hydrocarbon (HC), carbon monoxide (CO), and nitrogen oxide (NOx) emissions. The determination coefficient (R2) of experimental measured data and model predictions was close to 1, and the root-mean-squared error (RMSE) is close to zero. Additionally, the SVR model captured the corresponding trend of the engine with the input, though some existed small errors. In conclusion, these results indicated that the SVR model was suitable for the applications studied in this research.

Increasingly stringent regulations to reduce vehicle emissions have made it important to study emission mitigation strategies. Highly accurate control of the air-fuel ratio is an effective way to reduce emissions. However, a less accurate sensor can lead to reduced engine stability and greater variability in engine efficiency and emissions. Additionally, internal combustion engines (ICE) are moving toward higher compression ratios to achieve higher thermal efficiency and alleviate the energy crisis. The objective of this investigation was to analyze the significance of the accuracy of air-fuel ratio measurements at different compression ratios. In this study, a calibrated 1D CFD model was used to analyze the performance and emissions at different compression ratios. The results showed that carbon monoxide (CO) and nitrogen oxides (NOx) were sensitive to the equivalence ratio regardless of the compression ratio. With a slight change in the equivalence ratio, a high compression ratio had little effect on the change in engine performance and emissions. Moreover, with the same air-fuel ratio, an excessively high compression ratio (CR = 12) might result in knocking phenomenon, which increases the fluctuation of the engine output parameters and reduces engine stability. Overall, for precise control of combustion and thermal efficiency improvement, it is recommended that the measurement accuracy of the equivalence ratio is higher than 1% and the recommended value of the compression ratio are roughly 11.

GDI (Gasoline direct injection) technology is used in downsized engines for its economy and low emissions. However, if the injection strategy is not set properly, GDI will produce more emissions than conventional gasoline engines. In this paper, the effect of injection timing on GDI engine emissions under optimal phasing conditions was analyzed by using a three-dimensional (3D) computational fluid dynamics (CFD) GDI engine numerical model. The results showed that at medium engine speed and medium load advancing the injection timing from −300 to −290 CAD ATDC resulted in a more efficient and cleaner combustion process, as evidenced by the higher power output, the increased thermal and combustion efficiencies, and the reduced CO, UHC, soot emissions. The raised NOx emissions at advanced injection timing operation corresponded to the high combustion quality. There was a trade-off relation for advancing injection timing strategy. Specifically, an advanced injection timing operation would increase the amount of liquid film formed on the piston and liner, which is not favorable to clean combustion. However, advancing injection timing also provides more time for fuel-air mixing, which is beneficial for the formation of a more homogeneous mixture. The numerical simulations suggested that the advantages of earlier injection timing outweighed the disadvantages and improved engine efficiency, at least for the conditions and the engine investigated here. Moreover, the comparison indicated that changing injection timing also altered the chemical reaction pathways for pollutant species formation. Overall, all of these findings demonstrated that more fundamental work is still needed to understand the effect of injection timing on engine performance.