Abstract
1Increasing adoption of downsized, boosted, spark-ignition engines has improved vehicle fuel economy, and continued improvement is desirable to reduce carbon emissions in the near-term. However, this strategy is limited by damaging preignition events which can cause hardware failure. Research to date has shed light on various contributing factors related to fuel and lubricant properties as well as calibration strategies, but the causal factors behind an individual preignition cycle remain elusive. If actionable precursors could be identified, mitigation through active control strategies would be possible. This paper uses artificial neural networks to search for identifiable precursors in the cylinder pressure data from a large real-world data set containing many preignition cycles. It is found that while follow-up preignition cycles in clusters can be readily predicted, the initial preignition cycle is not predictable based on features of the cylinder pressure. This indicates that the alternating pattern of preignition cycles within clusters is influenced by the thermodynamic state as reflected in the pressure, but that the trigger for the initial preignition cycle is not thermodynamic in nature, but more likely tied to a critical threshold in the chemistry of the fuel/lubricant mixture in the upper crevice or other factors related to the presence of an ignition source.
Original language | English |
---|---|
Journal | SAE Technical Papers |
DOIs | |
State | Published - Oct 31 2023 |
Event | SAE 2023 Energy and Propulsion Conference and Exhibition (formerly called Powertrains, Fuels and Lubricants Conference and Exhibition), FFL 2023 - Greenville, United States Duration: Nov 7 2023 → Nov 9 2023 |
Funding
This research was conducted as part of the Partnership to Advance Combustion Engines (PACE) Consortium sponsored by the U.S. Department of Energy (DOE) Vehicle Technologies Office (VTO). The PACE Consortium is a collaborative project of multiple National Laboratories that combines unique experiments with world-class DOE computing and machine learning expertise to speed discovery of knowledge, improve engine design tools, and enable market-competitive powertrain solutions with potential for best-in-class lifecycle emissions. A special thanks to DOE VTO program managers Mike Weismiller and Gurpreet Singh. 1