Application and comparison of multiple machine learning models for the prediction of the laminar burning velocity for CH3OH/H2/air mixtures

Abstract

Recent investigations have indicated that co-firing CH3OH with H2 is a promising approach to develop a carbon-neutral energy system. However, accurate measurements of laminar burning velocities over a wide range of equivalence ratios, H2 mole fractions, pressures and temperatures are complicated and may not available. Hence, this research deeply investigates the application of several machine learning models in predicting the laminar burning velocities of CH3OH/H2 blended fuels. Results denoted that Random Forest Regressor is the most persuasive model based on a thorough comparison, as indicated by the correlation coefficient of 0.99707.