The use of neural network algorithms for modeling injection doses of modern fuel injectors

• Autorzy: Abramek Karol Franciszek , Osipowicz Tomasz , Mozga Łukasz

Identyfikatory

DOI

10.19206/CE-137959

• Języki publikacji: EN

Abstrakty

EN

The article presents the possibilities of using artificial intelligence methods to model the injection doses of a modern Common Rail (CR) fuel injector. The presented neural network solution belongs to the experimental models known as black boxes in mechatronics. The backpropagation algorithm and its Levenberg-Marquardt expansion were used for the simulation. The analysis showed that there is a good match between the measurements and the computational model. The proposed solution can be used in the processes of diagnosing not only elements of the injection equipment, but also the internal combustion engine.

Słowa kluczowe

EN

fuel injector; CI engine; Common Rail system; neural network; engine diagnosing

PL

wtryskiwacz paliwa; silnik o zapłonie samoczynnym; układ Common Rail; sieć neutronowa; diagnostyka silnika

• Wydawca: Polskie Towarzystwo Naukowe Silników Spalinowych
• Czasopismo: Combustion Engines
• Rocznik: 2021
• Tom: R. 60, nr 2
• Strony: 10--14
• Opis fizyczny: Bibliogr. 11 poz., 1 il., wykr.

Twórcy

autor

Abramek Karol Franciszek

• Faculty of Mechanical Engineering and Mechatronics at West Pomeranian University of Technology

• https://orcid.org/0000-0001-9704-5253

autor

Osipowicz Tomasz

• Faculty of Mechanical Engineering and Mechatronics at West Pomeranian University of Technology

• https://orcid.org/0000-0002-3321-7754

autor

Mozga Łukasz

• Faculty of Mechanical Engineering and Mechatronics at West Pomeranian University of Technology

• https://orcid.org/0000-0001-8015-6395

Bibliografia

• [1] OSIPOWICZ, T., ABRAMEK, K.F. Diagnosing methods common rail fuel injectors. Combustion Engines. 2017, 168(1), 56-61. https://doi.org/10.19206/CE-2017-109
• [2] OSIPOWICZ, T., ABRAMEK, K.F. The analysis of temperature disintegration on the body of fuel injector during research on test bench. Combustion Engines. 2017, 168(1), 172-177. https://doi.org/10.19206/CE-2017-128
• [3] ELIASZ, J., OSIPOWICZ, T., ABRAMEK, K.F., MOZGA, Ł. Model issues regarding modification of fuel injector components to improve the injection parameters of a modern compression ignition engine powered by biofuel. Applied Sciences. 2019, 9(24), 5479. https://doi.org/10.3390/app9245479
• [4] KNEFEL, T. Ocena techniczna wtryskiwaczy Common Rail na podstawie doświadczalnych badań przelewów. Eksploatacja i Niezawodnosc - Maintenance and Reliability. 2012, 14(1), 42-53.
• [5] RUTKOWSKI, L. Metody i techniki sztucznej inteligencji. Wydawnictwo Naukowe PWN. Warszawa 2012.
• [6] MARCIC, S., MARCIC, M., PRAUNSEIS Z. Mathematical model for the injector of a common rail fuel - injection system. Engineering. 2015, 7(6). https://doi.org/10.4236/eng.2015.76027
• [7] CAI, B., SUN, X., WANG, J. et al. Fault detection and diagnostic method of diesel engine by combining rule-based algorithm and BNs/BPNNs. Journal of Manufacturing Systems. 2020, 57(7), 148-157. https://doi.org/10.1016/j.jmsy.2020.09.001
• [8] KARAMI, R., RASUL, M.G., MASUD, M. et al. Experimental and computational analysis of combustion characteristics of a diesel engine fueled with diesel-tomato seed oil biodiesel blends. Fuel. 2021, 285, 119243. https://doi.org/10.1016/j.fuel.2020.119243
• [9] WANG, R., CHEN, H., GUAN, C. Random convolutional neural network structure: An intelligent health monitoring scheme for diesel engines. Measurement. 2021, 171, 108786. https://doi.org/10.1016/j.measurement.2020.108786
• [10] KUZHAGALIYEVA, N., THABET, A., SINGH, E. et al. Using deep neural networks to diagnose engine pre-ignition. Proceedings of the Combustion Institute. 2020, 38(4), 5915-5922. https://doi.org/10.1016/j.proci.2020.10.001
• [11] WANG, Y., LIU, N.N., GUO, H. et al. An engine-fault-diagnosis system based on sound intensity analysis and wavelet packet pre-processing neural network. Engineering Applications of Artificial Intelligence. 2020, 94, 103765. https://doi.org/10.1016/j.engappai.2020.103765

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).