Research on Combustion Characteristics of Flash-Boiling Spray in Cylinders Based on Machine Learning Methods

With the increasing number of vehicles in operation, exhaust emissions from engines have exerted negative impacts on ecological environments, prompting researchers to actively pursue cleaner and more efficient in-cylinder combustion strategies. Flash-boiling spray technology, capable of generating superior fuel atomization under relatively low injection pressures, has emerged as a promising approach for achieving performance breakthroughs in gasoline direct injection (GDI) engines. While current research primarily focuses on morphological characterization and mechanistic analysis of flashboiling spray, there remains insufficient understanding of flame development characteristics under flash boiling spray conditions within engine cylinders. This study systematically investigates the combustion characteristics of TPRF and PRF fuels under both subcooled and flash-boiling spray conditions through the integration of image processing and machine learning methodologies. Experimental investigations were conducted on an optically accessible GDI engine, with fuel temperatures maintained at 25°C (subcooled) and 180°C (flash-boiling). Machine learning-based analysis of in-cylinder flame features revealed that critical combustion characteristics can be effectively extracted through correlation matrices and Gini importance parameters, providing quantitative references for manual interpretation of flame development processes. Further comparative analysis demonstrated that subcooled conditions exhibited higher fractal dimensions and marginally faster combustion rates, while flash-boiling sprays significantly enhanced fuel-air mixing homogeneity, suppressed the formation of diffusion flames, and notably reduced aggregated soot particles.