Analysis of Flame Evolution Generated from Methyl Laurate Droplet Using Deep Learning

This research investigates the dynamic behavior of flames generated from methyl laurate droplets using advanced deep learning techniques. By analyzing high-resolution image sequences, we aim to extract valuable insights into the flame’s evolution, including its ignition, growth, and extinction phases. YOLOv9, a state-of-the-art object detection model, is employed to automatically segment and track key flame features such as flame shape, size, and intensity. Our results demonstrate a high accuracy of 0.97 and 0.92 mAP for automatic object segmentation of the flame and droplet. Through quantitative analysis of these features, we seek to gain a deeper understanding of the underlying physical processes governing droplet combustion. The results of this study can contribute to the development of more accurate and efficient combustion models, as well as improved fire safety strategies. This study investigates the combustion dynamics of methyl laurate droplets at atmospheric pressure, providing foundational insights into its behavior as a biodiesel fuel. Future research under high-pressure conditions is recommended to better understand its performance in practical engine applications.