A neuro-fuzzy based combustion sensor for the control of optimal engine combustion efficiency
Апстракт
Modern and advanced control systems for internal combustion engines require accurate feedback information from the combustion chamber. Whereas the in-cylinder pressure sensor provides this information through its close thermodynamic ties with the combustion process, drawbacks in its implementation push research towards other non-intrusive sensing methods. This paper suggests alternative methods of combustion phasing detection relying on measured angular crankshaft speed. Method developed, achieves sensing of angular position of the 50% of mass fraction burned (MFB50) through two steps: calculation of, so called, synthetic torque and its non-linear transformation to a combustion feature estimator through local model. In order to calibrate both parts of this virtual combustion sensor, parameters of a high-fidelity crankshaft dynamic model are identified, and the linear neuro-fuzzy based model is trained with extensive experimentally collected data set. Created virtual MFB50 sensor, demon...strated its performance, on a large test data set comprised of 70% of gathered data.
Кључне речи:
spark advance / neuro-fuzzy / MFB50 / Lolimot / internal combustion engine efficiency / combustion sensorИзвор:
Thermal Science, 2013, 17, 1, 135-151Издавач:
- Univerzitet u Beogradu - Institut za nuklearne nauke Vinča, Beograd
DOI: 10.2298/TSCI120703160M
ISSN: 0354-9836
WoS: 000315175600014
Scopus: 2-s2.0-84876999193
Колекције
Институција/група
Mašinski fakultetTY - JOUR AU - Miljić, Nenad AU - Tomić, Miroljub V. PY - 2013 UR - https://machinery.mas.bg.ac.rs/handle/123456789/1661 AB - Modern and advanced control systems for internal combustion engines require accurate feedback information from the combustion chamber. Whereas the in-cylinder pressure sensor provides this information through its close thermodynamic ties with the combustion process, drawbacks in its implementation push research towards other non-intrusive sensing methods. This paper suggests alternative methods of combustion phasing detection relying on measured angular crankshaft speed. Method developed, achieves sensing of angular position of the 50% of mass fraction burned (MFB50) through two steps: calculation of, so called, synthetic torque and its non-linear transformation to a combustion feature estimator through local model. In order to calibrate both parts of this virtual combustion sensor, parameters of a high-fidelity crankshaft dynamic model are identified, and the linear neuro-fuzzy based model is trained with extensive experimentally collected data set. Created virtual MFB50 sensor, demonstrated its performance, on a large test data set comprised of 70% of gathered data. PB - Univerzitet u Beogradu - Institut za nuklearne nauke Vinča, Beograd T2 - Thermal Science T1 - A neuro-fuzzy based combustion sensor for the control of optimal engine combustion efficiency EP - 151 IS - 1 SP - 135 VL - 17 DO - 10.2298/TSCI120703160M ER -
@article{ author = "Miljić, Nenad and Tomić, Miroljub V.", year = "2013", abstract = "Modern and advanced control systems for internal combustion engines require accurate feedback information from the combustion chamber. Whereas the in-cylinder pressure sensor provides this information through its close thermodynamic ties with the combustion process, drawbacks in its implementation push research towards other non-intrusive sensing methods. This paper suggests alternative methods of combustion phasing detection relying on measured angular crankshaft speed. Method developed, achieves sensing of angular position of the 50% of mass fraction burned (MFB50) through two steps: calculation of, so called, synthetic torque and its non-linear transformation to a combustion feature estimator through local model. In order to calibrate both parts of this virtual combustion sensor, parameters of a high-fidelity crankshaft dynamic model are identified, and the linear neuro-fuzzy based model is trained with extensive experimentally collected data set. Created virtual MFB50 sensor, demonstrated its performance, on a large test data set comprised of 70% of gathered data.", publisher = "Univerzitet u Beogradu - Institut za nuklearne nauke Vinča, Beograd", journal = "Thermal Science", title = "A neuro-fuzzy based combustion sensor for the control of optimal engine combustion efficiency", pages = "151-135", number = "1", volume = "17", doi = "10.2298/TSCI120703160M" }
Miljić, N.,& Tomić, M. V.. (2013). A neuro-fuzzy based combustion sensor for the control of optimal engine combustion efficiency. in Thermal Science Univerzitet u Beogradu - Institut za nuklearne nauke Vinča, Beograd., 17(1), 135-151. https://doi.org/10.2298/TSCI120703160M
Miljić N, Tomić MV. A neuro-fuzzy based combustion sensor for the control of optimal engine combustion efficiency. in Thermal Science. 2013;17(1):135-151. doi:10.2298/TSCI120703160M .
Miljić, Nenad, Tomić, Miroljub V., "A neuro-fuzzy based combustion sensor for the control of optimal engine combustion efficiency" in Thermal Science, 17, no. 1 (2013):135-151, https://doi.org/10.2298/TSCI120703160M . .