My personal experience with drones is quite limited. I certainly can’t fly one very well myself, and I’ve witnessed my boyfriend lose probably about a dozen of them to the wind, rooftops and trees. Although we haven’t had the best luck, industry is finding all kinds of uses for them, and is obviously much better at operating them than I am.
One of the most recent examples of this that I came across is from the Southwest Research Institute (SwRI), where a research team has developed a methane leak detection system as part of a U.S. Department of Energy (DOE) National Energy Technology Laboratory (NETL) project that aims to automate gas leak detection at oil and gas facilities.
A recent article on Phys.org, titled “Team using drones with machine learning to automate methane leak detection,” explains that the Smart Leak Detection System/Methane (SLED/M) detects leaks from above in real time. This project expands on the team’s previous development of a land-based SLED system that uses cameras and artificial intelligence (AI) to detect liquid hydrocarbon leaks.
Now, with the latest funding from the DOE NETL, the team is taking its previous development a step further by incorporating data collection and midwave infrared cameras on drones and developing machine learning algorithms to accurately detect leaks from above, Phys.org reports.
“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, in the article.
The new SLED/M can detect small methane leaks and reduce false positives using optimized algorithms that can detect leaks in many different environmental conditions, the article explains.
