Machine Learning-Enhanced Combustion Modelling: Predicting Ethanol Effects in a Single-Cylinder Research Engine

Recent studies highlight the urgent need to reduce greenhouse gas (GHG) emissions to mitigate the impacts of global warming and climate change. As a major contributor, the transport sector plays a vital role in these efforts. Ethanol emerges as a promising fuel for decarbonizing hard-to-electrify propulsion sectors, thanks to its sustainable production pathways and favourable physical and combustion properties—such as energy density, rapid burning velocity, and high knock resistance. This work proposes a methodology to enable the possibility of replicating the combustion behaviour of ethanol in a 1D CFD simulation environment representative of a single-cylinder research engine. Spark-ignition combustion is simulated through the Eddy Burn-Up combustion model previously calibrated for standard fossil gasoline. The combustion model features a laminar flame speed neural network, trained and tested through reference chemical kinetics simulations. The combustion model showed great accuracy in replicating key combustion metrics, highlighting its predictive capability while switching fuel kinds. Eventually, knock occurrence was evaluated by employing the Livengood-Wu induction time integral. The model was adjusted by the induction integral multiplier to align the knock predictions to the normalised experimental Mean Amplitude Pressure Oscillation value. The latest remains always below 1, meaning that the engine can be run at maximum combustion efficiency without knock occurrence even at maximum load.