SwRI uses drones to automate methane leak detection

A leak detection system developed by the Southwest Research Institute (SwRI) will be adapted to detect methane leaks in real-time from a drone.

The project is part of a collaboration between SwRI and the US Department of Energy’s (DOE) National Energy Technology Laboratory (NETL) to develop automated inspections of oil and gas facilities.

The Smart Leak Detection System/Methane (SLED/M) technology was developed with funding from the NETL. The institute also developed SLED technology, which uses cameras and artificial intelligence (AI) to detect liquid hydrocarbon leaks on pipelines and related facilities, including pump stations.

“After successfully developing SLED/M for stationary applications, such as fenceline monitoring of midstream facilities, we are advancing the technology to perform autonomously from drones,” said Maria Araujo, a manager in SwRI’s Critical Systems Department.

The technology is capable of detecting small methane leaks by pairing passing optical sensing data with AI algorithms.

New funding from the NETL will allow SwRI to collect data, test midwave infrared cameras on drone flights and develop machine learning algorithms to detect methane leaks.

“Drones and camera configurations present unique challenges because they capture data at different heights, distances and speeds,” added Araujo. “This funding enables development and testing to adapt the technology for commercial aerial inspections.”

The SLED/M technology reduces false positives and detects leaks that may otherwise go unnoticed, through optimising algorithms to reliably detect leaks under a range of environmental conditions.

“SwRI’s R&D investment in drone payloads and analytics aligns with our mission to advance science and technology that benefits government, industry and humankind,” said Dr. Steve Dellenback, vice-president of SwRI’s Intelligent Systems Division. “This effort is helping to address a significant challenge facing the world right now.”

155 queries in 0.670 seconds.