A growing portion of our pipeline infrastructure carries compressible fluids — NGLs such as ethane and propane, and liquefied olefins such as ethylene and propylene. These complex products behave in ways that expose the limits of conventional leak detection methods.
Flowstate has demonstrated the ability to use machine learning to enable improved leak detection on hazardous liquid pipelines. They have expanded their innovative approach to compressible fluids. The paper will introduce the approach and present validation results.