For immediate release
San Antonio — Oct. 11, 2016 — Southwest Research Institute (SwRI) is developing a methane leak detection system for the U.S. Department of Energy’s National Energy Technology Laboratory (NETL). The project, funded through a $798,000 DOE award, will develop an autonomous, real-time system to detect small methane leaks that are difficult to detect with current technology. SwRI will combine machine learning with passive optical sensing to identify small methane emissions using its Smart Methane Leak Detection technology, also known as SLED/M.
“There are systems that can detect large methane leaks, but it is challenging to effectively detect and mitigate small leaks unless you have inspection personnel with sensor devices stationed 24/7 across pipelines and other energy infrastructure,” said Maria Araujo, a manager in SwRI’s Intelligent Systems Division. “Our goal is to automate the process of finding small leaks in real-time.”
Another goal is to develop the SLED/M system for use across the entire natural gas supply chain from extraction and storage to transportation and distribution. Methane is the main molecule in natural gas and the most prevalent greenhouse gas emitted in the United States. While methane accounts for 11 percent of U.S. greenhouse gas emissions, it is considered more threatening than carbon dioxide because it absorbs heat more effectively.
The two-phase DOE project will take place over the next 18 months. In Phase I, SwRI will apply its liquid spill detection capabilities to develop the methane detection system using integrated optical sensors and an embedded processing unit to enable machine learning through algorithms that recognize patterns and trigger alarms during leak events.
With funding from its internal research and development program, SwRI applied machine learning technology to develop detection capabilities. A suite of algorithms processes data and identifies liquid hydrocarbon leaks. For the DOE project, SwRI will adapt its technology to identify gaseous methane leaks.
Phase II will focus on integrating and field-testing the system to document and demonstrate capabilities within a controlled environment.
“To broaden the industrial use of this technology, there should be no need for a human in the loop,” Araujo said. “We want a methane detection system that will detect small emissions within a few minutes with very few false alarms.”
In addition to the DOE project, SwRI has developed automated leak detection systems for other clients, including a solar-powered solution for the Methane Detectors Challenge, a multi-organizational collaboration that aims to curb methane emissions in the gas-producing sector.
For more information, contact Robert Crowe, (210) 522-4630, Communications Department, Southwest Research Institute, PO Drawer 28510, San Antonio, TX 78228-0510.