Edge AI Based Flare Monitoring to Reduce Global Warming

AGENDA:
Pre-register on Zoom:
6:40 SFBayACM Annual Meeting / Elections
7:00 Connection to Zoom chat with speaker and organizers
7:15 SFbayACM intro, upcoming events, introduce the speaker
7:25 presentation starts (~90 min with Q&A)

YouTube Live: https://youtu.be/eAMPFA4LCPM
ABSTRACT:
This video-based flare monitoring system is developed for real-time measurement of the flare gas flow rate at the edge. Depending on the desired trade-off between speed and accuracy, either an object detection (EfficientDet Dx) or instance segmentation (Mask R-CNN) model is used for real-time detection of flare and smoke instances in the input video stream. Organic and synthetic data is used to achieve high precision and recall (greater than 0.98) for both flare and smoke. The detected rectangular bounding boxes or polygon masks are used to estimate the flame size, and predict the flare gas exit velocity or equivalently flow rate. The estimated flow rate is within +/- 10% of a reference flow meter. The Deep Learning models are “edgified” in order to shrink the size and improve the inference speed by ~3X on small footprint edge devices. For three stacks in the camera’s field of view, the error increases to about +/- 25% of full scale due to the decreased resolution or increased scaling factor (~2.5X). The system components (camera and computing device) can be configured to obtain the desired tradeoff between cost, accuracy and measurement speed. This software product "Flare Advanced" has been deployed. The prior product "Flare Basic" has been deployed multiple times. You can not manage what you do not measure, this product helps to measure global warming emissions in real-time, sending alerts via email or SMS.

SPEAKER'S BIO:
Greg Makowski has been deploying data mining since 1992, has worked at 7 startups and has been through 4 acquisitions, including an acquisition by Johnson Controls in January 2022. While at the prior FogHorn Systems, his team developed and deployed 8+ software systems or solutions with deep learning, among other types of projects.

Himanshu Goyal is a graduate of IIT-Delhi, as of 2017. After his graduation, he worked with CITI bank in the TTS division. Here he developed a solution for the automation of day to day bank operations. He also had ventured into his own start-up to create an indoor surveillance system for gated communities. Next, he worked for Foghorn Systems as a Data Scientist, developing computer vision-based solutions for industrial applications. Foghorn was acquired by JohnsonControl on January 1, 2022.