08 Pipeline Integrity Management Applications Using High Fidelity Fiber Optic Monitoring & Machine Learning

Abstract

Distributed fiber optic sensing has been gaining significant momentum in pipeline industry adoption. While initial deployment of this technology has focused on preventative leak detection, new value-added applications continue to emerge which deliver data that are more oriented to long term pipeline integrity management and direct operational support.

Different fiber optic sensing technologies exist which can be appropriately leveraged for various applications.  High fidelity distributed sensing (HDS) achieves a very high signal-to-noise ratio (SNR), compared to other sensing or monitoring technologies.   Along with high SNR, HDS also provides integrated acoustics, temperature and strain/vibration, and is optimized to do so over long distances without degradation of fidelity.  This makes the HDS technology particularly appropriate for preventative pipeline leak detection as well as a number of other value-added applications which can leverage acoustics and either real time or cumulative strain/vibration measurements.  These cumulative strain measurements can be extremely valuable from a pipeline integrity perspective in terms of monitoring applications such as slope stability, ground subsidence, and other points of measured strain including a variety of pigging-related activities.

A recent novel application involved collaborating with a major producer (Suncor Energy) for the successful remediation of ovality issues with a segment of the pipe constructed via boring. The HDS data assisted in the process via monitoring of multiple pig-induced strain signatures as different construction techniques were used to sequentially alleviate the pipe ovality issue associated with the vertical pipeline loading, and a caliper pig was used during each individual sequential step. Such measurements bring direct operational savings, while also assisting the pipeline operator in understanding where the dynamic / elastic segments exist along the right-of-way and detecting strain anomalies in a spatial or temporal context.

Case studies will be provided to showcase the value of using supervised / unsupervised machine learning and high-fidelity distributed sensing to enable ground disturbance / security intrusions, geotechnical monitoring of earthquakes and slope movement, pig detection / real time pig tracking, as well as analysis of multiple pig runs. A specific case study will be provided to demonstrate how the cumulative strain analysis provided by the HDS technology contributed to the identification of the geohazard risks to a specific pipeline, leading to the ultimate decommissioning and relocation of the pipe.  Other “value added” applications such as flow monitoring of anomaly detection, flow rate, pressure, and density estimation will also be presented.

Read/Download PaperGradeAvailable after the event