Browsing by Author "Guner, Erdogan"

Now showing 1 - 2 of 2

Development of Optimal Diesel Injection Strategy Based on the Prediction of Performance and Emissions Using Deep Neural Network
(Sage Publications Ltd, 2023) Guner, Erdogan; Kaleli, Aliriza; Bakirci, Kadir; Ceviz, Mehmet Akif
This study aims to determine the optimal injection strategy by predicting the performance and exhaust emission parameters of a four-cylinder CRDI engine under several operating conditions. The experimental determination procedure is challenging and expensive calibration task since it requires a high number of tests. Many studies have focused on a limited level of parameters. In this study, design of experiments technique and deep neural network (DNN) modeling are used together. The experimental data set for the model is created using Taguchi L16 and L32 orthogonal arrays. The DNN model is developed to predict BSFC , N O x , HC, and CO emissions with speed, torque, injection timings and fuel quantities of each injection called as pilot1, pilot2, main, and post. In this way, it has become possible to evaluate the effects of a larger number of operating parameters in a wide range than the literature. The developed DNN model predicts the BSFC , N O-x , HC, and CO with R-2 0.939, 0.943, 0.963, and 0.966, respectively. Additionally, RMSE and MAE values for the model are between 0.024 and 0.048. The proposed method compared with the conventional look-up table method performs better in reducing the complexity and cost of experiments and exploration of the effects of injection parameters on engine emission and performance characteristics in a wide engine operating range. In conclusion, until 2300 rpm at specified torque (90 Nm), it is found that 70% of fuel quantity should inject in main injection to minimize BSFC and NOx emissions. The post injection quantity should be increased by reducing the amount of main injection from this operating condition on. Furthermore, it is observed that the ratios of pilot injection durations do not change with increasing engine speed, but quantity of first pilot injection is more than that of second pilot injection.
Exergy Analysis and Optimization of Multiple Injection Parameters of a Diesel Engine with Taguchi Method
(Taylor & Francis Inc, 2023) Guner, Erdogan; Kaltakkiran, Galip; Bakirci, Kadir; Ceviz, M. Akif
Multiple injection parameters have a significant effect on performance and emission formation in diesel engines. This study presents the optimization of these parameters with Taguchi method for different engine operating conditions. The experiments were conducted using four injections per cycle named Pilot1 (P1), Pilot2 (P2), Main (M), and Post (Po). The input parameters considered were injection timings and fuel quantities for each injection, while the output parameters were brake specific fuel consumption (BSFC) and nitrogen oxides (NOx) emissions. According to the results, the analysis of variance (ANOVA) shows that the durations of the P2 (D_P2) and Po (D_Po) and the start of the Main (SOI M) injection are very significant on BSFC and NOx emissions as independent of the engine speed. Based on contribution ratios at 1750 rpm and 2250 rpm operating conditions, D_Po is the most effective parameter on BSFC with 47.28% and 51.30%, while D_P2 has the greatest impact on NOx emissions with 37.96% and 61.80%, respectively. It is found from the optimization model obtained by using the Signal/Noise (S/N) ratios that injecting 5% of the total fuel in the post-injection phase could simultaneously improve BSFC and NOx emissions. Furthermore, the optimization model generally reduces heat loss exergy, exhaust exergy, and exergy destruction compared to the experimental values.