Prediction of ECN Spray—A Characteristics Using Machine Learning

Flame lift-off length (FLOL), ignition delay time (IDT), liquid length (LL), and Soot are essential parameters defining spray combustion characteristics. They help understand the combustion dynamics and validate the spray and combustion models for numerical simulations. However, obtaining extensive data from experiments is costlier and time-consuming. Machine learning (ML) models have advanced to the point where they could create efficient models that could be used as surrogates for experiments. In this study, five different ML algorithms have been trained using the experimental dataset available through the engine combustion network (ECN) community. A novel genetic algorithm-based hyperparameter optimization code has been used to optimize the models to improve prediction accuracy. The model performances were compared, and the better model was chosen as an experimental surrogate to predict FLOL, IDT, LL, and Soot.