Understanding Quantitative Performance of Large Standoff Magnetometry in Detecting Live Gas Pipeline Anomalies With Stress Estimation

Xu, Tianzong

doi:10.1115/ipc2018-78655

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, according to a recent report on gas pipeline incidents, the depth of buried pipelines is an important safety factor, as external interference to the pipeline is dramatically increased if the depth of cover becomes less than 80 cm [1]. ‡ Corresponding author For pipeline condition assessment, knowledge of the buried depth contributes to solving the inverse problem using recently developed large standoff magnetometry (LSM) technology [2,3,4], whereby stress conditions or abnormal features of the buried pipeline are determined through the remote magnetic field recorded by aboveground magnetometer surveys [5,6,4].…”

Section: Introductionmentioning

confidence: 99%

Determining the Depth and Location of Buried Pipeline by Magnetometer Survey

Staples

Cowell

et al. 2020

J. Pipeline Syst. Eng. Pract.

View full text Add to dashboard Cite

This paper proposes a new approach to determine the depth and location of buried pipelines using the remote magnetic field measured by aboveground magnetometer surveys. Calculation is presented and verified by the experimental results on 152-mm (6-in.) steel vessels. Performance of the technique is also evaluated through field trials against industrial pipe locators. The depth calculated from the measured magnetic field using this proposed technique agreed within the tolerance interval representing the confidence level of 99.7% of the depth determined by the industrial devices and was able to trend changes of the buried depth. In addition, it was possible to map the target pipeline using the survey route coordinates by calculating the lateral position of the survey route relative to the pipeline centreline from the measured magnetic field. So far, the depth measured by this proposed technique has shown a potential error of 8%. By producing 3-dimensional profile of buried pipelines through quick above-ground surveys, the proposed technique can be considered as a screening technique for asset and integrity management such as monitoring geohazards conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

Determining the Depth and Location of Buried Pipeline by Magnetometer Survey

Staples

Cowell

et al. 2020

J. Pipeline Syst. Eng. Pract.

View full text Add to dashboard Cite

show abstract

“…around defects, the magnetic behavior of the pipeline material changes locally due to the Villari magneto-restriction effect [1], [2]. Non-intrusive Large Stand-Off Magnetometry (LSM) technology has emerged as a promising tool in detecting small changes in the magnetic readings around defects associated with the regions of elevated stresses [1], [2], [3]. In addition to localizing the effects spatially, LSM's stress quantification has shown to provide insights into the properties of the defect in some cases [3].…”

Section: Introductionmentioning

confidence: 99%

“…Non-intrusive Large Stand-Off Magnetometry (LSM) technology has emerged as a promising tool in detecting small changes in the magnetic readings around defects associated with the regions of elevated stresses [1], [2], [3]. In addition to localizing the effects spatially, LSM's stress quantification has shown to provide insights into the properties of the defect in some cases [3]. A simplified schematic of the LSM is shown in Figure 1 with a multi-axial, multi-sensor alignment.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-based Anomaly Detection with Magnetic Data

Mitra¹,

Akhiyarov²,

Araya‐Polo³

et al. 2020

Preprint

View full text Add to dashboard Cite

Pipeline integrity is an important area of concern for the oil and gas, refining, chemical, hydrogen, carbon sequestration, and electric-power industries, due to the safety risks associated with pipeline failures. Regular monitoring, inspection, and maintenance of these facilities is therefore required for safe operation. Large standoff magnetometry (LSM) is a non-intrusive, passive magnetometer-based mea- surement technology that has shown promise in detecting defects (anomalies) in regions of elevated mechanical stresses. However, analyzing the noisy multi-sensor LSM data to clearly identify regions of anomalies is a significant challenge. This is mainly due to the high frequency of the data collection, mis-alignment between consecutive inspections and sensors, as well as the number of sensor measurements recorded. In this paper we present LSM defect identification approach based on ma- chine learning (ML). We show that this ML approach is able to successfully detect anomalous readings using a series of methods with increasing model complexity and capacity. The methods start from unsupervised learning with "point" methods and eventually increase complexity to supervised learning with sequence methods and multi-output predictions. We observe data leakage issues for some methods with randomized train/test splitting and resolve them by specific non-randomized splitting of training and validation data. We also achieve a 200x acceleration of support-vector classifier (SVC) method by porting computations from CPU to GPU leveraging the cuML RAPIDS AI library. For sequence methods, we develop a customized Convolutional Neural Network (CNN) architecture based on 1D convolutional filters to identify and characterize multiple properties of these defects. In the end, we report the scalability of the best-performing methods and compare them, for viability in field trials.

show abstract