Neural Network Soft Sensors for Gasoline Engine Exhaust Emission Estimation
- 12 November 2021
- journal article
- research article
- Published by Wiley in Journal of Energy Resources Technology
- Vol. 144 (8)
Abstract
Worldwide research and development programs aim to reduce harmful emissions from transportation vehicles. Soft sensors have shown great potentials to reduce cost and improve onboard diagnosis for vehicle emission control. In this work, two sets of soft sensors are proposed to predict the emissions and exhaust heat flux of a gasoline engine. Extensive steady-state measurement points over the entire engine operating conditions are collected for model training and validation, and the locally linear model tree learning method is adopted. The CO, NOx, hydrocarbon, exhaust temperature, and exhaust heat flux are estimated by the soft sensors under steady-state conditions. Training of CO, exhaust temperature, and exhaust heat flux models has achieved high model accuracy over the entire engine map. Local models are developed for NOx and HC emissions to improve model performance at different engine operating speed/load conditions, especially in the low emission zone. Model validation has shown correlation coefficients ranging 0.983 ∼ 0.999Keywords
This publication has 21 references indexed in Scilit:
- A New Approach for NOx Soft Sensors for the Aftertreatment of Diesel EnginesJournal of Physics: Conference Series, 2016
- Artificial neural network applications in the calibration of spark-ignition engines: An overviewEngineering Science and Technology, an International Journal, 2016
- Effects of engine parameters on ionization current and modeling of excess air coefficient by artificial neural networkApplied Thermal Engineering, 2015
- Diesel engine NOx emissions control: An advanced method for the O2 evaluation in the intake flowApplied Energy, 2014
- Soft sensor for and using dynamic neural networksComputers and Electrical Engineering, 2009
- Emission reduction during TWC warm-up: control synthesis and hardware-in-the-loop verificationInternational Journal of Modelling, Identification and Control, 2008
- Performance and exhaust emissions of a gasoline engine using artificial neural networkApplied Thermal Engineering, 2007
- Extracting the main patterns of natural time series for long-term neurofuzzy predictionNeural Computing and Applications, 2006
- Local Versus Global Models for Classification ProblemsThe American Statistician, 2003
- Control of diesel enginesIEEE Control Systems, 1998