Comparative Study on Combustion Features Extraction Methods in IC Engines Using Neural Networks Models
Апстракт
The in-cylinder pressure analysis provides important information on the combustion process and stands as an invaluable tool in the internal combustion engine research & development. Its implementation in a combustion control algorithms appears as a promising solution for attaining optimal combustion control in IC Engines. The pressure sensor durability, accuracy and price, along with increased demand for the processing power of Engine ECU, seems to be the main obstacles for putting these concept in IC engines on serial production line. This paper deals with the potentials of Artificial Neural Networks (ANN) and their application in combustion features extraction, based on the crankshaft angular speed measurements. High speed processing capabilities and acceptable accuracy of ANN make them good candidates to become a core component of the future combustion control algorithms. An radial basis function (RBF) ANN and a local linear Neuro-fuzzy model (LLNFM) are compared in order to gain so...me conclusions on optimal network topology, best suited for job of extracting crucial combustion features on common ECU platforms.
Кључне речи:
engine combustion analysis / neural networks / spark advance / crankshaft dynamicsИзвор:
International Congress Motor Vehicles & Motors 2012, 2012, 159-172Издавач:
- Faculty of Engineering, University of Kragujevac
Финансирање / пројекти:
- Истраживање и развој алтернативних погонских система и горива за градске аутобусе и комунална возила ради побољшања енергетске ефикасности и еколошких карактеристика (RS-MESTD-Technological Development (TD or TR)-35042)
Колекције
Институција/група
Mašinski fakultetTY - CONF AU - Miljić, Nenad AU - Tomić, Miroljub V. AU - Popović, Slobodan AU - Kitanović, Marko AU - Mrđa, Predrag D. PY - 2012 UR - https://machinery.mas.bg.ac.rs/handle/123456789/4597 AB - The in-cylinder pressure analysis provides important information on the combustion process and stands as an invaluable tool in the internal combustion engine research & development. Its implementation in a combustion control algorithms appears as a promising solution for attaining optimal combustion control in IC Engines. The pressure sensor durability, accuracy and price, along with increased demand for the processing power of Engine ECU, seems to be the main obstacles for putting these concept in IC engines on serial production line. This paper deals with the potentials of Artificial Neural Networks (ANN) and their application in combustion features extraction, based on the crankshaft angular speed measurements. High speed processing capabilities and acceptable accuracy of ANN make them good candidates to become a core component of the future combustion control algorithms. An radial basis function (RBF) ANN and a local linear Neuro-fuzzy model (LLNFM) are compared in order to gain some conclusions on optimal network topology, best suited for job of extracting crucial combustion features on common ECU platforms. PB - Faculty of Engineering, University of Kragujevac C3 - International Congress Motor Vehicles & Motors 2012 T1 - Comparative Study on Combustion Features Extraction Methods in IC Engines Using Neural Networks Models EP - 172 SP - 159 UR - https://hdl.handle.net/21.15107/rcub_machinery_4597 ER -
@conference{ author = "Miljić, Nenad and Tomić, Miroljub V. and Popović, Slobodan and Kitanović, Marko and Mrđa, Predrag D.", year = "2012", abstract = "The in-cylinder pressure analysis provides important information on the combustion process and stands as an invaluable tool in the internal combustion engine research & development. Its implementation in a combustion control algorithms appears as a promising solution for attaining optimal combustion control in IC Engines. The pressure sensor durability, accuracy and price, along with increased demand for the processing power of Engine ECU, seems to be the main obstacles for putting these concept in IC engines on serial production line. This paper deals with the potentials of Artificial Neural Networks (ANN) and their application in combustion features extraction, based on the crankshaft angular speed measurements. High speed processing capabilities and acceptable accuracy of ANN make them good candidates to become a core component of the future combustion control algorithms. An radial basis function (RBF) ANN and a local linear Neuro-fuzzy model (LLNFM) are compared in order to gain some conclusions on optimal network topology, best suited for job of extracting crucial combustion features on common ECU platforms.", publisher = "Faculty of Engineering, University of Kragujevac", journal = "International Congress Motor Vehicles & Motors 2012", title = "Comparative Study on Combustion Features Extraction Methods in IC Engines Using Neural Networks Models", pages = "172-159", url = "https://hdl.handle.net/21.15107/rcub_machinery_4597" }
Miljić, N., Tomić, M. V., Popović, S., Kitanović, M.,& Mrđa, P. D.. (2012). Comparative Study on Combustion Features Extraction Methods in IC Engines Using Neural Networks Models. in International Congress Motor Vehicles & Motors 2012 Faculty of Engineering, University of Kragujevac., 159-172. https://hdl.handle.net/21.15107/rcub_machinery_4597
Miljić N, Tomić MV, Popović S, Kitanović M, Mrđa PD. Comparative Study on Combustion Features Extraction Methods in IC Engines Using Neural Networks Models. in International Congress Motor Vehicles & Motors 2012. 2012;:159-172. https://hdl.handle.net/21.15107/rcub_machinery_4597 .
Miljić, Nenad, Tomić, Miroljub V., Popović, Slobodan, Kitanović, Marko, Mrđa, Predrag D., "Comparative Study on Combustion Features Extraction Methods in IC Engines Using Neural Networks Models" in International Congress Motor Vehicles & Motors 2012 (2012):159-172, https://hdl.handle.net/21.15107/rcub_machinery_4597 .