2009
DOI: 10.1109/tmag.2009.2020160
|View full text |Cite
|
Sign up to set email alerts
|

Machine Learning Techniques for the Analysis of Magnetic Flux Leakage Images in Pipeline Inspection

Abstract: The magnetic flux leakage (MFL) technique is commonly used for non-destructive testing of oil and gas pipelines. This testing involves the detection of defects and anomalies in the pipe wall, and the evaluation of the severity of these defects. The difficulty with the MFL method is the extent and complexity of the analysis of the MFL images. In this paper we show how modern machine learning techniques can be used to considerable advantage in this respect. We apply the methods of support vector regression, kern… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
26
0

Year Published

2011
2011
2021
2021

Publication Types

Select...
5
4
1

Relationship

0
10

Authors

Journals

citations
Cited by 88 publications
(26 citation statements)
references
References 30 publications
0
26
0
Order By: Relevance
“…The core idea of segmentation threshold compression algorithms is that in the place where the original amplitude of the signal is relatively large little or no compression can be used, and in the smaller amplitude areas large compression ratios are chosen. Noise reduction is needed to improve the signal quality and increase the accuracy of data analysis [ 73 , 74 ].…”
Section: Measurement and Processingmentioning
confidence: 99%
“…The core idea of segmentation threshold compression algorithms is that in the place where the original amplitude of the signal is relatively large little or no compression can be used, and in the smaller amplitude areas large compression ratios are chosen. Noise reduction is needed to improve the signal quality and increase the accuracy of data analysis [ 73 , 74 ].…”
Section: Measurement and Processingmentioning
confidence: 99%
“…The big data sets that must be analyzed by the systems result in a strong need of implementation of new processing algorithms. The procedures should be responsible, at the same time, for data collection, transformation, pattern search, and decision making [ 12 , 16 , 17 , 18 , 19 , 20 , 21 ]. An example of such an approach is the use of machine learning algorithms to automatically search even very complex relations between a large amount of input data [ 17 , 18 , 20 , 21 , 22 , 23 ].…”
Section: Introductionmentioning
confidence: 99%
“…A comparative study between magneticand ultrasonic-based inspection techniques is reported in [28]. The authors in [29] proposed and compared three machine learning approaches, namely, support vector machine, kernelized principal component analysis, and kernelized partial least squares, to filter the sensor noise.…”
Section: Introductionmentioning
confidence: 99%