Artificial Neural Network-Based Emission Control for Future ICE Concepts

2023-01-1605

10/31/2023

Features
Event
Energy & Propulsion Conference & Exhibition
Authors Abstract
Content
The internal combustion engine contains several actuators to control engine performance and emissions. These are controlled within the engine ECU and follow a specific operating strategy to achieve objectives such as NOx reduction and fuel economy. However, these two goals are conflicting and a compromise is required. The operating state depends on system constraints such as engine speed, load, temperature levels, and aftertreatment system efficiency. This results in constantly changing target values to stay within the defined limits, especially the legal emission limits. The conventional approach is to use multiple operating modes. Each mode represents a specific compromise and is activated accordingly. Multiple modes are required to meet emissions regulations under all required conditions, which increases the calibration effort. This new control approach uses an artificial neural network to replace the conventional multiple mode approach. The desired engine emission and temperature limits, for example based on SCR conversion efficiency, are sent to the artificial neural network, which controls the actuators to meet the desired limits. It also enables the lowest possible fuel consumption or, for example, the highest possible exhaust gas enthalpy within the given system state. A simulation environment was created to investigate the benefits of this approach. A cold heavy-duty emission cycle was simulated with the conventional and the new approach. While both approaches had the same tailpipe NOx emissions during the emission cycle, the new approach achieved a fuel consumption reduction of 0.9%. Since this method allows semi-automatic calibration and training of the artificial neural network, the manual calibration effort can be reduced compared to the conventional approach as an additional advantage. In conclusion, this study introduced a new approach to the control of the internal combustion engine and demonstrated through simulations that the new control approach can further optimize the synergies between the engine and the exhaust gas aftertreatment.
Meta TagsDetails
DOI
https://doi.org/10.4271/2023-01-1605
Pages
10
Citation
Wetering, M., Danninger, A., and Vos, B., "Artificial Neural Network-Based Emission Control for Future ICE Concepts," SAE Technical Paper 2023-01-1605, 2023, https://doi.org/10.4271/2023-01-1605.
Additional Details
Publisher
Published
Oct 31, 2023
Product Code
2023-01-1605
Content Type
Technical Paper
Language
English