MFL signals and artificial neural networks applied to detection and classification of pipe weld defects

Carvalho, A. A.; Rebello, J. M. A.; Sagrilo, Luís Volnei Sudati; Camerini, Cláudio; Miranda, I.V.J.

doi:10.1016/j.ndteint.2006.04.003

Cited by 134 publications

(54 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MFL ILI tools used to detect, locate, and size pipeline anomalies, such as metal loss, dents, and ferrous metal objects, are based on the change of magnetic flux leakage in air near the pipe wall detected by the hall sensor (shown in Figure 2) [17][18][19]. Though it will be affected by piping stress deformation, cleanness of pipeline, lift off of probe, and the vibration when tool running, the accuracy and resolution of this technology is industrially accepted and world-widely used [20,21].…”

Section: Features Of Mfl Signalsmentioning

confidence: 99%

New Method to Identify Field Joint Coating Failures Based on MFL In-Line Inspection Signals

Dai

Wang²,

Deng

et al. 2018

Coatings

View full text Add to dashboard Cite

Above ground indirect detections and random excavations that have applied the past years for buried long distance oil and gas pipelines can only identify some damaged coating locations. Hence, large number of field joint coating (FJC) failures happen unconsciously until they lead to failures of the pipelines. Based on the analysis of magnetic flux leakage (MFL) in-line inspection (ILI) signals, combined with the statistical results of 414 excavations from two different pipeline sections, a new method to identify the failed FJC is established. Though it can only identify FJC failures when there are signs of corrosion on pipe body, it is much more efficient and cost-saving. The concluded identification rule still needs more validations and improvements to be more applicable and accuracy.

show abstract

Section: Features Of Mfl Signalsmentioning

confidence: 99%

New Method to Identify Field Joint Coating Failures Based on MFL In-Line Inspection Signals

Dai

Wang²,

Deng

et al. 2018

Coatings

View full text Add to dashboard Cite

show abstract

“…The results shown that it is possible to classify signals of classes of defect and non-defect using NN with 94.2 % efficiency. Moreover, the algorithm is possible to classify the defect pattern signals using neural networks with an average rate of success of 71.7 % for the validation set [17]. Estimation of length and width of the metal-loss profiles from the 1-D signal of the defects has been carried out.…”

Section: Introductionmentioning

confidence: 99%

Magnetic Flux Leakage (MFL) based Defect Characterization of Steam Generator Tubes using Artificial Neural Networks

Daniel¹,

Abudhahir²,

Paulin³

2017

Journal of Magnetics

View full text Add to dashboard Cite

“…Carvalho et al [16] realized the location of defects by using neural networks. However, the large extent of the calculations is made by this procedure.…”

Section: Introductionmentioning

confidence: 99%

Extracting the region of interest from MFL signals

Sadr¹,

Okhovat²

2016

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Abstract:In this paper, we study the magnetic flux leakage (MFL) signals for detection of defects in ferromagnetic materials. MFL signals consist of a background that is not constant and is combined with noise. Since there are slight variations because of noise, any large distortion shows a defect. Here the estimation of the background and then the determination of a threshold to distinguish defects from noise have been used for locating defects. In this method, precise evaluation of these two parameters has a vital role on the defect detection. The concept of histograms has been employed for eliminating the effect of defects in computing background signal. Results show that this algorithm is fast enough and yields detection of more defects that have lower amplitude. In the next step, an appropriate value for the threshold is determined by considering a trade-off between defect detection rate and noise separation rate.

show abstract

MFL signals and artificial neural networks applied to detection and classification of pipe weld defects

Cited by 134 publications

References 9 publications

New Method to Identify Field Joint Coating Failures Based on MFL In-Line Inspection Signals

New Method to Identify Field Joint Coating Failures Based on MFL In-Line Inspection Signals

Magnetic Flux Leakage (MFL) based Defect Characterization of Steam Generator Tubes using Artificial Neural Networks

Extracting the region of interest from MFL signals

Contact Info

Product

Resources

About