English

Data-driven Analysis of Turbulent Flame Images

Computer Vision and Pattern Recognition 2020-12-04 v1

Abstract

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 CH4_4/air premixed flames with CO2_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% CO2_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.

Keywords

Cite

@article{arxiv.2012.01485,
  title  = {Data-driven Analysis of Turbulent Flame Images},
  author = {Rathziel Roncancio and Jupyoung Kim and Aly El Gamal and Jay P. Gore},
  journal= {arXiv preprint arXiv:2012.01485},
  year   = {2020}
}

Comments

AIAA Science and Technology Conference 2021

R2 v1 2026-06-23T20:41:05.708Z