The timely detection of small leaks from liquid pipelines poses a significant challenge for pipeline operations. Distributed Temperature Sensing (DTS) is a common External Leak Detection (ELD) system. DTS allows for high accuracy temperature measurements over long distances. Unexpected deviations in temperature at any given location can indicate various physical changes in the environment, including contact with a heated hydrocarbon due to a pipeline leak.
The signals stemming from small pipeline leaks are not significantly greater than the signal noise floor, so care must be taken to configure the system in a manner that can detect small leaks while minimizing false alarms. DTS systems must be tuned to the nominal temperature profile along individual pipeline segments. This customization allows for significant sensitivity and can utilize different leak detection thresholds at various locations based on normal temperature patterns. This segment-specific tuning requires a significant amount of resources and time. Additionally, this process must be repeated as pipeline and environmental conditions change over time. Thus, there is a significant need and interest in advancing existing DTS processing techniques to enable the detection of leaks that today go undetected by current DTS algorithms.
This paper discusses the recent work focused on using machine learning (ML) techniques for which models were trained to detect leak signatures. Initial proof-of-concept results provide a more robust methodology for detecting leaks and also allow for the detection of smaller leaks than are currently detectable by typical DTS systems, with low false alarm rates. A key use of ML approaches is that the system can “learn” about a given pipeline on its own without the need to utilize resources for pipeline segment-specific tuning. The potential to have a self-taught system is a powerful concept, and this paper discusses some key initial findings from a test application.