Application of back-propagation neural networks to defect characterization using eddy current testing

2020 ◽  
Vol 64 (1-4) ◽  
pp. 817-825
Author(s):  
Xinwu Zhou ◽  
Ryoichi Urayama ◽  
Tetsuya Uchimoto ◽  
Toshiyuki Takagi
Keyword(s):  
Neural Networks ◽  
Eddy Current ◽  
Back Propagation ◽  
Eddy Current Testing ◽  
Defect Characterization ◽  
Current Testing ◽  
Conductive Materials ◽  
Back Propagation Neural Networks ◽  
Lift Off ◽  
Relative Errors

Eddy current testing is widely used for the automatic detection of defects in conductive materials. However, this method is strongly affected by probe scanning conditions and requires signal analysis to be carried out by experienced inspectors. In this study, back-propagation neural networks were used to predict the depth and length of unknown slits by analyzing eddy current signals in the presence of noise caused by probe lift-off and tilting. The constructed neural networks were shown to predict the depth and length of defects with relative errors of 4.6% and 6.2%, respectively.

scholarly journals Research on Detection Mechanism of Weld Defects of Carbon Steel Plate Based on Orthogonal Axial Eddy Current Probe

Sensors ◽  
2020 ◽  
Vol 20 (19) ◽  
pp. 5515
Author(s):  
Linnan Huang ◽  
Chunhui Liao ◽  
Xiaochun Song ◽  
Tao Chen ◽  
Xu Zhang ◽  
...  
Keyword(s):  
Carbon Steel ◽  
Eddy Current ◽  
Steel Plate ◽  
Difficult Problem ◽  
Eddy Current Testing ◽  
Detection Sensitivity ◽  
Detection Mechanism ◽  
Current Testing ◽  
Weld Defects ◽  
Lift Off

The uneven surface of the weld seam makes eddy current testing more susceptible to the lift-off effect of the probe. Therefore, the defect of carbon steel plate welds has always been a difficult problem in eddy current testing. This study aimed to design a new type of eddy current orthogonal axial probe and establish the finite element simulation model of the probe. The effect of the probe structure, coil turns, and coil size on the detection sensitivity was simulated. Further, a designed orthogonal axial probe was used to conduct a systematic experiment on the weld of carbon steel specimens, and the 0.2 mm width and 1 mm depth of weld defects of carbon steel plates were effectively detected. The experimental results showed that the new orthogonal axial eddy current probe effectively suppressed the unevenness effect of the weld surface on the lift-off effect during the detection process.

scholarly journals Evaluation of Coating Thickness Using Lift-Off Insensitivity of Eddy Current Sensor

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 419
Author(s):  
Xiaobai Meng ◽  
Mingyang Lu ◽  
Wuliang Yin ◽  
Abdeldjalil Bennecer ◽  
Katherine J. Kirk
Keyword(s):  
Eddy Current ◽  
Coating Thickness ◽  
Thickness Measurement ◽  
Eddy Current Testing ◽  
Thickness Variation ◽  
Testing Technique ◽  
Current Testing ◽  
Thin Skin ◽  
Embedded Algorithms ◽  
Lift Off

Defect detection in ferromagnetic substrates is often hampered by nonmagnetic coating thickness variation when using conventional eddy current testing technique. The lift-off distance between the sample and the sensor is one of the main obstacles for the thickness measurement of nonmagnetic coatings on ferromagnetic substrates when using the eddy current testing technique. Based on the eddy current thin-skin effect and the lift-off insensitive inductance (LII), a simplified iterative algorithm is proposed for reducing the lift-off variation effect using a multifrequency sensor. Compared to the previous techniques on compensating the lift-off error (e.g., the lift-off point of intersection) while retrieving the thickness, the simplified inductance algorithms avoid the computation burden of integration, which are used as embedded algorithms for the online retrieval of lift-offs via each frequency channel. The LII is determined by the dimension and geometry of the sensor, thus eliminating the need for empirical calibration. The method is validated by means of experimental measurements of the inductance of coatings with different materials and thicknesses on ferrous substrates (dual-phase alloy). The error of the calculated coating thickness has been controlled to within 3% for an extended lift-off range of up to 10 mm.

Differential coupling double-layer coil for eddy current testing with high lift-off

2021 ◽  
pp. 1-1
Author(s):  
Kefan Chen ◽  
Bin Gao ◽  
G.Y. Tian ◽  
Yupei Yang ◽  
Changrong Yang ◽  
...  
Keyword(s):  
Double Layer ◽  
Eddy Current ◽  
Eddy Current Testing ◽  
High Lift ◽  
Current Testing ◽  
Lift Off ◽  
Differential Coupling

Inversion of lift-off distance and thickness for non-magnetic metal using eddy current testing

2020 ◽  
pp. 1-1
Author(s):  
Xiaobai Meng ◽  
Mingyang Lu ◽  
Wuliang Yin ◽  
Abdeldjalil Bennecer ◽  
Katherine J Kirk
Keyword(s):  
Eddy Current ◽  
Eddy Current Testing ◽  
Current Testing ◽  
Magnetic Metal ◽  
Lift Off

scholarly journals The Effects of Lift-Off from Wall Thinning Signal in Pulsed Eddy Current Testing

2012 ◽  
Vol 17 (4) ◽  
pp. 298-301 ◽  
Author(s):  
Duck-Gun Park ◽  
C.S. Angani ◽  
M.B. Kishore ◽  
C.G. Kim ◽  
D.H. Lee
Keyword(s):  
Eddy Current ◽  
Eddy Current Testing ◽  
Current Testing ◽  
Pulsed Eddy Current ◽  
Wall Thinning ◽  
Lift Off

scholarly journals Evaluation of Coating Thickness Using Lift-Off Insensitivity of Eddy Current Sensor

2021 ◽  
Author(s):  
Xiaobai Meng ◽  
Mingyang Lu ◽  
Wuliang Yin ◽  
Abdeldjalil Bennecer ◽  
Katherine Kirk
Keyword(s):  
Eddy Current ◽  
Coating Thickness ◽  
Thickness Measurement ◽  
Eddy Current Testing ◽  
Thickness Variation ◽  
Testing Technique ◽  
Current Testing ◽  
Thin Skin ◽  
Embedded Algorithms ◽  
Lift Off

Defect detection in ferromagnetic substrates is often hampered by non-magnetic coating thickness variation when using conventional eddy current testing technique. The lift-off distance between the sample and the sensor is one of the main obstacles for the thickness measurement of non-magnetic coatings on ferromagnetic substrates when using the eddy current testing technique. Based on the eddy current thin-skin effect and the lift-off insensitive inductance (LII), a simplified iterative algorithm is proposed for reducing the lift-off variation effect using a multi-frequency sensor. Compared to the previous techniques on compensating the lift-off error (e.g., the lift-off point of intersection) while retrieving the thickness, the simplified inductance algorithms avoid the computation burden of integration, which are used as embedded algorithms for the online retrieval of lift-offs via each frequency channel. The LII is determined by the dimension and geometry of the sensor, thus eliminating the need for empirical calibration. The method is validated by means of experimental measurements of the inductance of coatings with different materials and thicknesses on ferrous substrates (dual-phase alloy). The error of the calculated coating thickness has been controlled to within 3 % for an extended lift-off range of up to 10 mm.

Impedance inversion in eddy current testing of layered planar structures via neural networks

1997 ◽  
Vol 30 (2) ◽  
pp. 69-74 ◽  
Author(s):  
I.T. Rekanos ◽  
T.P. Theodoulidis ◽  
S.M. Panas ◽  
T.D. Tsiboukis
Keyword(s):  
Neural Networks ◽  
Eddy Current ◽  
Eddy Current Testing ◽  
Current Testing ◽  
Planar Structures ◽  
Impedance Inversion

The combination of adaptive database SDM and multi-output SVM for eddy current testing

2015 ◽  
Vol 34 (6) ◽  
pp. 1731-1739 ◽  
Author(s):  
M. Chelabi ◽  
T. Hacib ◽  
Z. Belli ◽  
M. R. Mekideche ◽  
Y. Le Bihan
Keyword(s):  
Eddy Current ◽  
Eddy Current Testing ◽  
Learning Performance ◽  
Support Vector ◽  
Inversion Method ◽  
Defect Characterization ◽  
Content Type ◽  
Current Testing ◽  
Svm Model ◽  
Schema Design

Purpose – Eddy current testing (ECT) is a nondestructive testing method for the detection of flaws that uses electromagnetic induction to find defects in conductive materials. In this method, eddy currents are generated in a conductive material by a changing magnetic field. A defect is detected when there is a disruption in the flow of the eddy current. The purpose of this paper is to develop a new noniterative inversion methodology for detecting degradation (defect characterization) such as cracking, corrosion and erosion from the measurement of the impedance variations. Design/methodology/approach – The methodology is based on multi-output support vector machines (SVM) combined with the adaptive database schema design method (SDM). The forward problem was solved numerically using finite element method (FEM), with its accuracy experimentally verified. The multi-output SVM is a statistical learning method that has good generalization capability and learning performance. FEM is used to create the adaptive database required to train the multi-output SVM and the genetic algorithm is used to tune the parameters of multi-output SVM model. Findings – The results show the applicability of multi-output SVM to solve eddy current inverse problems instead of using traditional iterative inversion methods which can be very time-consuming. With the experimental results the authors demonstrate the accuracy which can be provided by the multi-output SVM technique. Practical implications – The work allows extending the capability of the experimentation ECT defect characterization system developed at LGEP. Originality/value – A new inversion method is developed and applied to ECT defect characterization. This new concept introduces multi-output SVM in the context of ECT. The real data together with estimated one obtained by multi-output SVM model are compared in order to evaluate the effectiveness of the developed technique.

Sign in / Sign up

Export Citation Format

Share Document