Data-driven Analysis of Turbulent Flame Images
This work provides a data-driven method for characterizing unburned material pockets in turbulent flames, which is important for engineers and researchers studying power generation using gas turbines, particularly for understanding transient events and reducing emissions.
This paper investigated unburned material pockets in turbulent CH$_4$/air premixed flames with CO$_2$ addition using OH Planar Laser-Induced Fluorescence images. A Convolutional Neural Network (CNN) model was developed to classify images containing these pockets, achieving accuracies of 91.72%, 89.35%, and 85.80% for flames with 0%, 5%, and 10% CO$_2$ addition, respectively.
Turbulent premixed flames are important for power generation using gas turbines. Improvements in characterization and understanding of turbulent flames continue particularly for transient events like ignition and extinction. Pockets or islands of unburned material are features of turbulent flames during these events. These features are directly linked to heat release rates and hydrocarbons emissions. Unburned material pockets in turbulent CH$_4$/air premixed flames with CO$_2$ addition were investigated using OH Planar Laser-Induced Fluorescence images. Convolutional Neural Networks (CNN) were used to classify images containing unburned pockets for three turbulent flames with 0%, 5%, and 10% CO$_2$ addition. The CNN model was constructed using three convolutional layers and two fully connected layers using dropout and weight decay. The CNN model achieved accuracies of 91.72%, 89.35% and 85.80% for the three flames, respectively.