Diesel engine NOx emission modeling using a new experiment design and reduced set of regressors

Alcan, Gökhan and Ünel, Mustafa and Aran, Volkan and Yılmaz, Metin and Gürel, Çetin and Köprübaşı, Kerem (2018) Diesel engine NOx emission modeling using a new experiment design and reduced set of regressors. In: Proceedings of 18th IFAC Symposium on System Identification (SYSID 2018), Stockholm, Sweden

[thumbnail of SYSID18_SysID_Paper208.pdf] PDF
SYSID18_SysID_Paper208.pdf

Download (558kB)

Abstract

n this paper, NOx emissions from a diesel engine are modeled with nonlinear autoregressive with exogenous input (NARX) model. Airpath and fuelpath channels are excited by chirp signals where the frequency profile of each channel is generated by increasing the number of sweeps. Past values of the output are employed only in linear prediction with all input regressors, and the most significant input regressors are selected for the nonlinear prediction by orthogonal least square (OLS) algorithm and error reduction ratio. Experimental results show that NOx emissions can be modeled with high validation performance and models obtained using a reduced set of regressors perform better in terms of stability and robustness.
Item Type: Papers in Conference Proceedings
Subjects: T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL1-484 Motor vehicles. Cycles
T Technology > TJ Mechanical engineering and machinery > TJ163.12 Mechatronics
Divisions: Faculty of Engineering and Natural Sciences > Academic programs > Mechatronics
Faculty of Engineering and Natural Sciences
Depositing User: Mustafa Ünel
Date Deposited: 14 Aug 2018 14:49
Last Modified: 26 Apr 2022 09:30
URI: https://research.sabanciuniv.edu/id/eprint/35804

Actions (login required)

View Item
View Item