Hydrogen Mixtures Flammability Limits Prediction Using Machine Learning Models

Predictions on flammability limits (FLs) had been conducted using semi-empirical and fully empirical models, which are either limited in scope of application and/or affected by significant methodical prediction errors. Some parameters influencing the FLs are not considered in the non-comprehensive empirical models. In the present study, optimized multilayer perceptron (MLP) models are investigated to improve the accuracy of the prediction of FLs in dependance from the temperature and any inert gas admixtures. Different input features constituted by the flammability state, mixture composition, initial mixture temperature, adiabatic flame temperature, and Lewis numbers were implemented into the MLP model. Data limitation challenges were addressed using data augmentation. The best model indicated averaged deviations comparable to the respective experimental FLs determination errors. The models also indicated comparable performances in comparison to the empirical models while having a broader range of applicability. This approach seeks to improve FLs prediction accuracy and calculation time necessary, minimizing FLs determination experimental efforts.