CRDI Engine Emission Prediction Models with Injection Parameters Based on ANN and SVM to Improve the SOOT-NOx Trade-Off

Liao, W. R.; Shi, J. H.; Li, G. X.

doi:10.47176/jafm.16.10.1801

CRDI Engine Emission Prediction Models with Injection Parameters Based on ANN and SVM to Improve the SOOT-NOx Trade-Off

Document Type : Regular Article

Authors

¹ College of Mechanical and Electrical Engineering, Changjiang Institute of Technology, Wuhan, Hubei Province, 430212, China

² College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan, Shanxi Province, 030024, China

10.47176/jafm.16.10.1801

Abstract

Artificial Neural Network (ANN) and Support Vector Machine (SVM) have been widely used to solve non-linear problems. In the current study, based on 112 groups of experimental data, ANN and SVM models were established and compared to improve the trade-off relationship between SOOT and NOx emissions of a Common Rail Diesel Injection (CRDI) engine fueled with Fischer-Tropsch (F-T) diesel under different operating conditions and injection parameters. The model parameters for the different predictive targets were selected by evaluating the mean square error (MSE) and determination coefficient. Compared to the number of network iterations, the number of implied nodes had a greater effect on the MSE of the ANN model. Compared to the penalty parameter, the width coefficient had a weaker impact on the SVM performance. A comparative analysis showed that the SVM had better predictive accuracy and generalization ability than the ANN, with a maximum error not exceeding five percent and a determination coefficient of over 0.9. Subsequently, the optimal SVM model was combined with the NSGA-II algorithm to determine the optimal injection parameters for the CRDI engine, resulting in solutions to simultaneously decrease the SOOT and NOx emissions. The optimized injection parameters resulted in a 3.7–7.1% reduction in SOOT emission and a 1.2–2.6% reduction in NOx emissions compared to the original engine operating conditions. Based on limited experimental samples, SVM is inferred to be a useful tool for predicting the exhaust emissions of engines fueled with F-T diesel and can provide support for optimizing injection parameters.

Keywords

Main Subjects

Combustion and Reactive Flows

References

Aydın, M., Uslu, S., & Bahattin Çelik, M. (2020). Performance and emission prediction of a compression ignition engine fueled with biodiesel-diesel blends: A combined application of ANN and RSM based optimization. Fuel, 269, 117472. https://doi.org/https://doi.org/10.1016/j.fuel.2020.117472##

Bittencout, F. R., & Zárate, L. E. (2011). Hybrid structure based on previous knowledge and GA to search the ideal neurons quantity for the hidden layer of MLP—Application in the cold rolling process. Applied Soft Computing, 11(2), 2460-2471. https://doi.org/https://doi.org/10.1016/j.asoc.2010.10.002##

Chandran, D. (2020). Compatibility of diesel engine materials with biodiesel fuel. Renewable Energy, 147, 89-99. https://doi.org/https://doi.org/10.1016/j.renene.2019.08.040##

Dhande, D. Y., Choudhari, C. S., Gaikwad, D. P., & Dahe, K. B. (2022). Development of artificial neural network to predict the performance of spark ignition engine fuelled with waste pomegranate ethanol blends. Information Processing in Agriculture. https://doi.org/https://doi.org/10.1016/j.inpa.2022.05.001##

Duan, H., Huang, Y., Mehra, R. K., Song, P., & Ma, F. (2018). Study on influencing factors of prediction accuracy of support vector machine (SVM) model for NOx emission of a hydrogen enriched compressed natural gas engine. Fuel, 234, 954-964. https://doi.org/https://doi.org/10.1016/j.fuel.2018.07.009##

Emiroğlu, A. O., & Şen, M. (2018). Combustion, performance and exhaust emission characterizations of a diesel engine operating with a ternary blend (alcohol-biodiesel-diesel fuel). Applied Thermal Engineering, 133, 371-380. https://doi.org/https://doi.org/10.1016/j.applthermaleng.2018.01.069##

Fu, J., Yang, R., Li, X., Sun, X., Li, Y., Liu, Z., Zhang, Y., & Sunden, B. (2022). Application of artificial neural network to forecast engine performance and emissions of a spark ignition engine. Applied Thermal Engineering, 201, 117749. https://doi.org/https://doi.org/10.1016/j.applthermaleng.2021.117749##

Guardiola, C., López, J. J., Martín, J., & García-Sarmiento, D. (2011). Semiempirical in-cylinder pressure based model for NOX prediction oriented to control applications. Applied Thermal Engineering, 31(16), 3275-3286. https://doi.org/https://doi.org/10.1016/j.applthermaleng.2011.05.048##

Gürgen, S., Ünver, B., & Altın, İ. (2018). Prediction of cyclic variability in a diesel engine fueled with n-butanol and diesel fuel blends using artificial neural network. Renewable Energy, 117, 538-544. https://doi.org/https://doi.org/10.1016/j.renene.2017.10.101##

Hao, B., Song, C., Lv, G., Li, B., Liu, X., Wang, K., & Liu, Y. (2014). Evaluation of the reduction in carbonyl emissions from a diesel engine using Fischer–Tropsch fuel synthesized from coal. Fuel, 133, 115-122. https://doi.org/https://doi.org/10.1016/j.fuel.2014.05.025##

Hao, D., Mehra, R. K., Luo, S., Nie, Z., Ren, X., & Fanhua, M. (2020). Experimental study of hydrogen enriched compressed natural gas (HCNG) engine and application of support vector machine (SVM) on prediction of engine performance at specific condition. International Journal of Hydrogen Energy, 45(8), 5309-5325. https://doi.org/https://doi.org/10.1016/j.ijhydene.2019.04.039##

Huang, Z., Huang, J., Luo, J., Hu, D., & Yin, Z. (2022). Performance enhancement and emission reduction of a diesel engine fueled with different biodiesel-diesel blending fuel based on the multi-parameter optimization theory. Fuel, 314, 122753. https://doi.org/https://doi.org/10.1016/j.fuel.2021.122753##

Jiao, Y., Liu, R., Zhang, Z., Yang, C., Zhou, G., Dong, S., & Liu, W. (2019). Comparison of combustion and emission characteristics of a diesel engine fueled with diesel and methanol-Fischer-Tropsch diesel-biodiesel-diesel blends at various altitudes. Fuel, 243, 52-59. https://doi.org/https://doi.org/10.1016/j.fuel.2019.01.107##

Kavitha, R., & Mukesh Kumar, P. C. (2018). A Comparison between MLP and SVR Models in Prediction of Thermal Properties of Nano Fluids. Journal of Applied Fluid Mechanics, 11, 7-14. https://doi.org/10.36884/jafm.11.SI.29411##

Kim, Y. D., Yang, C. W., Kim, B. J., Moon, J. H., Jeong, J. Y., Jeong, S. H., Lee, S. H., Kim, J. H., Seo, M. W., Lee, S. B., Kim, J. K., & Lee, U. D. (2016). Fischer–tropsch diesel production and evaluation as alternative automotive fuel in pilot-scale integrated biomass-to-liquid process. Applied Energy, 180, 301-312. https://doi.org/https://doi.org/10.1016/j.apenergy.2016.07.095##

Krishnamoorthi, M., Malayalamurthi, R., & Sakthivel, R. (2019). Optimization of compression ignition engine fueled with diesel - chaulmoogra oil - diethyl ether blend with engine parameters and exhaust gas recirculation. Renewable Energy, 134, 579-602. https://doi.org/https://doi.org/10.1016/j.renene.2018.11.062##

Meenal, R., & Selvakumar, A. I. (2018). Assessment of SVM, empirical and ANN based solar radiation prediction models with most influencing input parameters. Renewable Energy, 121, 324-343. https://doi.org/https://doi.org/10.1016/j.renene.2017.12.005##

Molina, S., Guardiola, C., Martín, J., & García-Sarmiento, D. (2014). Development of a control-oriented model to optimise fuel consumption and NOX emissions in a DI Diesel engine. Applied Energy, 119, 405-416. https://doi.org/https://doi.org/10.1016/j.apenergy.2014.01.021##

Neves, R. C., Klein, B. C., da Silva, R. J., Rezende, M. C. A. F., Funke, A., Olivarez-Gómez, E., Bonomi, A., & Maciel-Filho, R. (2020). A vision on biomass-to-liquids (BTL) thermochemical routes in integrated sugarcane biorefineries for biojet fuel production. Renewable and Sustainable Energy Reviews, 119, 109607. https://doi.org/https://doi.org/10.1016/j.rser.2019.109607##

Niu, X., Yang, C., Wang, H., & Wang, Y. (2017). Investigation of ANN and SVM based on limited samples for performance and emissions prediction of a CRDI-assisted marine diesel engine. Applied Thermal Engineering, 111, 1353-1364. https://doi.org/https://doi.org/10.1016/j.applthermaleng.2016.10.042##

Pastor, J. V., García, A., Micó, C., & Lewiski, F. (2020). An optical investigation of Fischer-Tropsch diesel and Oxymethylene dimethyl ether impact on combustion process for CI engines. Applied Energy, 260, 114238. https://doi.org/https://doi.org/10.1016/j.apenergy.2019.114238##

Poggio, T., & Girosi, F. (1990). Regularization algorithms for learning that are equivalent to multilayer networks. Science, 247(4945), 978-982.##

Şener, R. (2022). Numerical Investigation of Ducted Fuel Injection Strategy for Soot Reduction in Compression Ignition Engine. Journal of Applied Fluid Mechanics, 15(2), 475-489. https://doi.org/10.47176/jafm.15.02.33088##

Shamshirband, S., Tabatabaei, M., Aghbashlo, M., Yee, P. L., & Petković, D. (2016). Support vector machine-based exergetic modelling of a DI diesel engine running on biodiesel–diesel blends containing expanded polystyrene. Applied Thermal Engineering, 94, 727-747. https://doi.org/https://doi.org/10.1016/j.applthermaleng.2015.10.140##

Shi, J., Wang, T., Zhao, Z., Wu, Z., & Zhang, Z. (2019). Cycle-to-Cycle Variation of a Diesel Engine Fueled with Fischer–Tropsch Fuel Synthesized from Coal. Applied Sciences, 9(10), 2032. https://www.mdpi.com/2076-3417/9/10/2032##

Shi, J., Wang, T., Zhao, Z., Yang, T., & Zhang, Z. (2018). Experimental Study of Injection Parameters on the Performance of a Diesel Engine with Fischer–Tropsch Fuel Synthesized from Coal. Energies, 11(12), 3280-3292. https://www.mdpi.com/1996-1073/11/12/3280##

Sivamani, S., Udayakumar, M., & Sellappan, N. (2022). Prediction of single cylinder direct injection diesel engine performance fuelled with lemon peel oil biodiesel using artificial neural network. Materials Today: Proceedings. https://doi.org/https://doi.org/10.1016/j.matpr.2022.10.197##

Soloiu, V., Wiley, J. T., Gaubert, R., Mothershed, D., Carapia, C., Smith, R. C., Williams, J., Ilie, M., & Rahman, M. (2020). Fischer-Tropsch coal-to-liquid fuel negative temperature coefficient region (NTC) and low-temperature heat release (LTHR) in a constant volume combustion chamber (CVCC). Energy, 198, 117288. https://doi.org/https://doi.org/10.1016/j.energy.2020.117288##

Vapnik, V. N. (2000). The Nature of Statistical Learning Theory. The Nature of Statistical Learning Theory. https://doi.org/https://doi.org/10.1007/978-1-4757-3264-1_1##

Vishwanathan, G., & Reitz, R. D. (2015). Application of a semi-detailed soot modeling approach for conventional and low temperature diesel combustion – Part I: Model performance. Fuel, 139, 757-770. https://doi.org/https://doi.org/10.1016/j.fuel.2014.08.026##

Zhao, F., Yang, W., Zhou, D., Yu, W., Li, J., & Tay, K. L. (2017). Numerical modelling of soot formation and oxidation using phenomenological soot modelling approach in a dual-fueled compression ignition engine. Fuel, 188, 382-389. https://doi.org/https://doi.org/10.1016/j.fuel.2016.10.054##