- R&D 100 Awards
The Smart LEak Detection (SLED) system uses optical sensor fusion and machine learning to reliably and autonomously detect small liquid pipeline leaks of hazardous chemicals in real-time. Between 2007 and 2012, leaks in the U.S. hazardous liquid pipelines network exceeded 100,000 barrels a year, a 3.5 percent increase from the previous five-year period. This expansion of leak events, combined with the increasing amount of pipeline infrastructure near urban centers and environmentally sensitive areas, has renewed the focus on the detection of leaks in hazardous liquid pipelines. The SLED system uses machine learning techniques to reliably detect the chemical fingerprint of small liquid leaks. The technology can be deployed using a variety of mobile and stationary platforms and can nimbly adjust to different sensors and technologies. Developed to detect liquid hydrocarbon leaks, the technology is also being adapted to detect gaseous leaks as well, specifically methane, in a U.S. Department of Energy-funded project. The Southwest Research Institute is also investigating the possibility of adapting the technology for remote sensing from satellite platforms to locate offshore oil spills.