A Machine Learning Approach for Engine Model-Based Control on NOx Emissions

Features
Event
2023 JSAE/SAE Powertrains, Energy and Lubricants International Meeting
Authors Abstract
Content
Increasingly stringent regulations on engine emissions require strict control of nitrogen oxide (NOx) emissions in diesel engines. Feedback control systems coupled with virtual sensors for real-time NOx readings have shown to be effective solutions for managing emissions. The authors of this paper propose a machine learning approach for developing a virtual NOx sensor implemented on an Engine Control Unit (ECU) of a YANMAR diesel engine. A Random Forest model was trained on data comprising Ramped Modal Cycles (RMCs) and Non-Road Transient Cycles (NRTCs) with a focus on robustness with respect to engine-to-engine variability in ECU sensor reading. Despite strong constraints imposed on the complexity of the model due to the limited computing power of the ECU, good prediction performance was obtained on both cycles (R2 = 1.0 on RMCs and R2 = 0.967 on NRTCs). The present study shows that machine learning models trained on transient data can play an important role in developing robust NOx emissions control systems on diesel engines.
Meta TagsDetails
DOI
https://doi.org/10.4271/2023-32-0157
Pages
10
Citation
Latinov, M., Fiorini, N., Vichi, G., Innocenti, A. et al., "A Machine Learning Approach for Engine Model-Based Control on NOx Emissions," Advances and Current Practices in Mobility 6(3):1574-1582, 2024, https://doi.org/10.4271/2023-32-0157.
Additional Details
Publisher
Published
Sep 29, 2023
Product Code
2023-32-0157
Content Type
Journal Article
Language
English