Prediction of Laminar Burning Speed of Propane/Hydrogen/Air Mixtures Using Power-Law Correlation and Two Machine Learning Models

Abstract Propane (C3H8) and hydrogen (H2) are regarded as alternative fuels that favorable to the environment. Hydrogen gas's low energy density, storage, transportation main issues with using it an fuel. Addition of gas in combustion propane will also improve flame stability, broaden lean flammability limits, reduces pollutant emissions. Thus, utilizing mixtures fuel is a good choice. Laminar burning speed fundamental property combustible mixture can be used provide information regarding mixture’s reactivity, exothermicity, diffusivity. In this study, power-law correlation machine learning methods were create models predict laminar propane/hydrogen/air at various states. Two artificial neural network (ANN) support vector (SVM). The data generated by CANTRA code chemical kinetic mechanism. For wide variety input values, able determine great accuracy. ANN model yields best performance. advantage these noticeably faster computing time when compared reaction mechanisms.