Access the full text.
Sign up today, get DeepDyve free for 14 days.
Loading next page...
/lp/iospress/automated-detection-of-defects-in-eddy-current-inspection-data-using-wnWrCvME0C
References (19)
-
Deng W (2020)
Defect image recognition and classification for eddy current testing of titanium plate based on convolutional neural networkComplexity, 2020
-
SMOTE: Synthetic Minority Over-sampling Technique
-
L Breiman (2001)
Random forestsMach Learn, 45
-
XGBoost
-
Grimberg R (2011)
Eddy current examination of steam generator tubes from PHWR power plants using rotating magnetic field transducerInt J Microstruct Mater Prop, 6
-
Random Forests
-
Classification and Quantitative Evaluation of Eddy Current Based on Kernel-PCA and ELM for Defects in Metal Component
-
Obrutsky L (2009)
Overview of steam generator tube-inspection technologySpec Issue e-J Nondestruct Test (eJNDT), 14
-
MRPC eddy current flaw classification in tubes using deep neural networks
-
Automated eddy current data analysis
-
W Deng, B Ye, J Bao (2019)
Classification and quantitative evaluation of eddy current based on Kernel-PCA and ELM for defects in metal componentMetals (Basel), 9
-
Shuaib Ahmed S (2016)
Multidimensional radial basis function neural network for sizing flaws from eddy current imagesJ Nondestruct Test Eval (J Indian Soc Nondestruct Test), 14
-
J Park, S-J Han, N Munir (2019)
MRPC Eddy current flaw classification in tubes using deep neural networksNucl Eng Technol, 51
-
HL Libby (1979)
Introduction to electromagnetic nondestructive test methods
-
An Adaptive Sampling Protocol for Real-Time Defect Assessment Using Eddy Current Sensor and Machine Learning Algorithm
-
Thirunavukkarasu S (2004)
Quantitative eddy current testing using radial basis function neural networksMater Eval, 62
-
C Dutta, SP Sagar, A Kumar (2023)
An adaptive sampling protocol for real-time defect assessment using eddy current sensor and machine learning algorithmIEEE Trans Ind Appl, 59
-
R Grimberg, A Savin, S Leitrim (2011)
Automated eddy current data analysisInt J Mater Prod Technol, 41
-
NV Chawla, KW Bowyer, LO Hall (2002)
SMOTE: synthetic minority over-sampling techniqueJ Artif Intell Res, 16
- Publisher
- IOS Press
- Copyright
- © The Author(s) 2025
- ISSN
- 1383-5416
- eISSN
- 1875-8800
- DOI
- 10.1177/13835416251344938
- Publisher site
- See Article on Publisher Site
Abstract
In this study, automated detection of defects in eddy current (EC) impedance signals is explored using Machine Learning (ML) methods. A feature based classification has been proposed with three features which are derived based on similarity and closeness. XGBoost, Random Forest and Radial Basis Function Neural Network models were implemented and applied on a heat exchanger tube EC inspection data. The performance of the ML models were assessed based on the accuracy, precision and recall metrics. The ML models are able to correctly classify the occurrence of defect events in EC impedance data with an accuracy of 99%. This work lays a foundation for creating more robust and effective systems for automated detection of defects.
Journal
International Journal of Applied Electromagnetics and Mechanics – IOS Press
Published: Jan 1, 2025
Keywords: Eddy current testing; machine learning; template based correlation; distance time warping; XGBoost; Random Forest; Radial Basis Function Neural Network