This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Machine-Learning-Based Emission Models in Gasoline Powertrains—Part 2: Virtual Carbon Monoxide
- Nathan J. Kempema - Ford Motor Company, Research & Advanced Engineering, USA ,
- Conner Sharpe - Ford Motor Company, Global Data, Insights & Analytics, USA ,
- Xiao Wu - Ford Motor Company, Global Data, Insights & Analytics, USA ,
- Mehrdad Shahabi - Ford Motor Company, Global Data, Insights & Analytics, USA ,
- David Kubinski - Ford Motor Company, Research & Advanced Engineering, USA
Journal Article
03-16-06-0045
ISSN: 1946-3936, e-ISSN: 1946-3944
Sector:
Topic:
Citation:
Kempema, N., Sharpe, C., Wu, X., Shahabi, M. et al., "Machine-Learning-Based Emission Models in Gasoline Powertrains—Part 2: Virtual Carbon Monoxide," SAE Int. J. Engines 16(6):799-807, 2023, https://doi.org/10.4271/03-16-06-0045.
Language:
English
Abstract:
In this work, tailpipe carbon monoxide emission from a gasoline powertrain case
study vehicle was analyzed for off-cycle (i.e., on road) driving to develop a
virtual sensor. The vehicle was equipped with a portable emissions measurement
system (PEMS) that measured carbon monoxide concentration and exhaust volumetric
flowrate to calculate the mass of carbon monoxide emitted from the tailpipe. The
vehicle was also equipped with a tailpipe electrochemical NOx sensor,
and a correlation between its linear oxygen signal and the PEMS-measured carbon
monoxide concentration was observed. The NOx sensor linear oxygen
signal depends on the concentration of several reducing species, and a machine
learning model was trained using this data and other features to target the
PEMS-measured carbon monoxide mass emission. The model demonstrated a mean
absolute percentage error (MAPE) of 19% when using 15 training drive cycles.
Finally, a virtual carbon monoxide sensor was developed by removing the tailpipe
NOx sensor information from the model feature set and predicting
tailpipe carbon monoxide mass. The virtual model MAPE was shown to increase by
5% compared to the earlier version with a tailpipe NOx sensor over
the same number of training, validation, and test drive cycles. The minimal
degradation in accuracy for the virtual model was hypothesized to result from
the fact that narrowband oxygen sensors may contain information regarding how
rich or lean the exhaust gas is compared to stoichiometric conditions. This is
analogous to the information provided by a wide-band oxygen sensor, but
potentially with reduced resolution and accuracy. The data-driven approach was
able to produce a novel virtual tailpipe carbon monoxide sensor in a gasoline
powertrain using only common powertrain and emission sensors.