Three-axial MFL inspection in pipelines for defect imaging using a hybrid inversion procedure

被引：10

作者：

Chen J. ^{[1
]}

机构：

[1] Electric Power Planning and Engineering Institute, Beijing

来源：

Insight: Non-Destructive Testing and Condition Monitoring | 2016年 / 58卷 / 06期

关键词：

Defect imaging; Magnetic flux leakage; Neural networks; Taboo search algorithms;

D O I：

10.1784/insi.2016.58.6.302

中图分类号：

学科分类号：

摘要：

This paper proposes a hybrid inversion procedure to reconstruct three-dimensional (3D) defect profiles from three-axial magnetic flux leakage (MFL) signals in pipeline inspection. The characteristics of three-axial MFL signals are firstly explored to guide the inspection of defects. The radial basis function (RBF) neural network is utilised to predict an initial defect profile and a taboo search-based iterative inversion procedure is developed to search for the globally optimum defect profile. In the iterative inversion procedure, a two-stage taboo search optimising strategy is utilised to accelerate the inversion process. Experiments of defect imaging are carried out based on both measured and simulated three-axial MFL signals. The experiment results demonstrate that the proposed hybrid inversion procedure is rather effective in accuracy, robustness and practicality.

引用

页码：302 / 307

页数：5

共 18 条

[1]

Khodayari-Rostamabad A., Reilly J.P., Nikolova N.K., Hare J.R., Pasha S., Machine learning techniques for the analysis of magnetic flux leakage images in pipeline inspection, IEEE Transactions on Magnetics, 45, pp. 3073-3084, (2009)

[2]

Amineh R.K., Nikolova N.K., Reilly J.P., Hare J.R., Characterisation of surface-breaking cracks using one tangential component of magnetic leakage field measurements, IEEE Transactions on Magnetics, 44, pp. 516-524, (2008)

[3]

Li Y., Wilson J., Tian G.Y., Experiment and simulation study of 3D magnetic field sensing for magnetic flux leakage defect characterisation, NDT&E International, 40, pp. 179-184, (2007)

[4]

Chen J., Huang S., Zhao W., Three-dimensional defect reconstruction from magnetic flux leakage signals in pipeline inspection based on a dynamic taboo search procedure, Insight: Non-Destructive Testing and Condition Monitoring, 56, 10, pp. 535-540, (2014)

[5]

Kopp G., Willems H., Sizing limits of metal loss anomalies using tri-axial MFL measurements: A model study, NDT&E International, 55, pp. 75-81, (2013)

[6]

Ramuhalli P., Udpa L., Udpa S.S., Electromagnetic NDE signal inversion by function-approximation neural networks, IEEE Transactions on Magnetics, 38, 6, pp. 3633-3642, (2002)

[7]

Joshi A., Wavelet transform and neural network-based 3D defect characterisation using magnetic flux leakage, International Journal of Applied Electromagnetics and Mechanics, 28, pp. 149-153, (2008)

[8]

Amineh R.K., Koziel S., Nikolova N.K., Bandler J.W., Reilly J.P., A space mapping methodology for defect characterisation from magnetic flux leakage measurements, IEEE Transactions on Magnetics, 44, pp. 2058-2065, (2008)

[9]

Chen J., Huang S., Zhao W., Reconstruction of 3D defect profiles from MFL signals using radial wavelet basis function neural network, International Journal of Applied Electromagnetics and Mechanics, 45, 1, pp. 465-471, (2014)

[10]

Ramuhalli P., Udpa L., Udpa S.S., Neural network-based inversion algorithms in magnetic flux leakage non-destructive evaluation, Journal of Applied Physics, 93, pp. 8274-8276, (2003)

← 1 2 →