A Deep Learning Model for Predicting the Laminar Burning Velocity of NH₃/H₂/Air

Abstract

Both NH3 and H2 are considered to be carbon-free fuels, and their mixed combustion has excellent performance. Considering the laminar burning velocity as a key characteristic of fuels, accurately predicting the laminar burning velocity of NH3/H2/Air is crucial for its combustion applications. The study made improvements to the XGBoost model and developed NH3/H2/Air Laminar Burning Velocity Net (NHLBVNet), which adopts a composite hierarchical structure to connect the functions of feature extraction, feature combination, and model prediction. The dataset consists of 487 sets of experimental data after the exclusion of outliers. The correlation coefficient (R2 > 0.99) of NHLBVNet is higher than that of the XGBoost model (R2 > 0.93). Robustness experiment results indicate that this model can obtain more accurate prediction results than other models even under small sample datasets.

Keywords

• laminar burning velocity (LBV)
• deep learning
• NH3/H2/Air
• XGBoost
• predicting method