# Flame quality monitoring of flare stack based on deep visual features

arXiv: https://arxiv.org/abs/2410.19823 · HTML: https://mlsanity.com/paper/2410.19823/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 15 references that are in the map.
- First posted on arXiv 18 Oct 2024.

## Builds on (most cited first, 5 of 5)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [A Tutorial on Principal Component Analysis](https://mlsanity.com/paper/1404.1100/) (2014)
- [Logical Neural Networks](https://mlsanity.com/paper/2006.13155/) (2020)

## Abstract (arXiv)

Flare stacks play an important role in the treatment of waste gas and waste materials in petroleum fossil energy plants. Monitoring the efficiency of flame combustion is of great significance for environmental protection. The traditional method of monitoring with sensors is not only expensive, but also easily damaged in harsh combustion environments. In this paper, we propose to monitor the quality of flames using only visual features, including the area ratio of flame to smoke, RGB information of flames, angle of flames and other features. Comprehensive use of image segmentation, target detection, target tracking, principal component analysis, GPT-4 and other methods or tools to complete this task. In the end, real-time monitoring of the picture can be achieved, and when the combustion efficiency is low, measures such as adjusting the ratio of air and waste can be taken in time. As far as we know, the method of this paper is relatively innovative and has industrial production value.