Intelligent Flaw Detection in Eddy Current Inspection Data Through Machine Learning Model
Source abstract
Abstract
The paper presents a robust machine learning model for automated classification of flaw signals from eddy current inspection data of heat exchanger tubes. The proposed model employs four sliding window based ingenious features namely variance, template correlation, template dynamic time warping distance and area under the signal with Random Forest supervised machine learning model, to identify flaws. The efficacy of the model is evaluated on tube inspection data acquired in a heat exchanger by comparing its performance against expert analysis. The machine learning model exhibits an impressive accuracy of 99.94% for classification of flaw signals in addition to higher desirable metrics such as precision, recall, F1-score and Matthews correlation coefficient (MCC). This work lays a strong foundation for developing a real-time, robust and reliable flaw detection system.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Non-Destructive Testing Techniques · Welding Techniques and Residual Stresses · Ultrasonics and Acoustic Wave Propagation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (34)
Show source-provided references
1. Baldev Raj, T., Jayakumar, Rao, B.P.C.: Non-destructive testing and evaluation for structural integrity, Sadhana, vol. 20, pp. 5–38, (1995). https://doi.org/10.1007/BF0274728210.1007/BF02747282 ↗
2. García-Martín, J., Gómez-Gil, J., Vázquez-Sánchez, E.: Non-destructive techniques based on eddy current testing, Sensors, vol. 11, no. 3, pp. 2525–2565, (2011). https://doi.org/10.3390/s11030252510.3390/s110302525 ↗
3. Abdalla, A.N., Faraj, M.A., Samsuri, F., Rifai, D., Ali, K., Al-Douri, Y.: Challenges in improving the performance of eddy current testing. Rev. Meas. Control. 52, 1–2 (2019). https://doi.org/10.1177/002029401880138210.1177/0020294018801382 ↗
4. Valery Lunin and Andrey Zhdanov: Automated data analysis in eddy current inspection of steam generator tubes, Proceedings of the 9th European Conference on NDT, pp. 1–7, (2006)
5. Udpa, L., Ramuhalli, P., Benson, J., Udpa, S.: Automated analysis of eddy current signals in steam generator tube inspection, Proceedings of the 16th World Conference on NDT (WCNDT), (2004). https://www.ndt.net/?id=2182
6. Munir, N., Huang, J., Wong, C.N., Song, S.J.: Machine learning based eddy current testing: A review. Results Eng. p. 103724 (2024). https://doi.org/10.1016/j.rineng.2024.10372410.1016/j.rineng.2024.103724 ↗
7. Zheng, X., She, S., Xia, Z., Xiong, L., Zou, X., Yu, K., Guo, R., Zhu, R., Zhang, Z., Yin, W.: Analyzing the permeability distribution of multilayered specimens using pulsed eddy-current testing with multi-scale 1D-ResNet. NDT E Int. p. 149, 103247 (2025). https://doi.org/10.1016/j.ndteint.2024.10324710.1016/j.ndteint.2024.103247 ↗
8. Machado, M., Araújo: Luís Filipe Soldado Granadeiro rosado, Nuno Alberto Marques mendes, Rosa Maria Mendes miranda, and Telmo Jorge gomes Dos santos, new directions for inline inspection of automobile laser welds using non-destructive testing. Int. J. Adv. Manuf. Technol. p. 1–13 (2022). https://doi.org/10.1007/s00170-021-08007-010.1007/s00170-021-08007-0 ↗
9. Ricci, M., Silipigni, G., Ferrigno, L., Laracca, M., Adewale, I.D., Tian, G.Y.: Evaluation of the lift-off robustness of eddy current imaging techniques. NDT E Int. p. 85, 43–52 (2017). https://doi.org/10.1016/j.ndteint.2016.10.00110.1016/j.ndteint.2016.10.001 ↗
10. She, S., Zheng, X., Xiong, L., Meng, T., Zhang, Z., Shao, Y., Yin, W.: Jialong shen, and Yunze he,thickness measurement and Surface-Defect detection for metal plate using pulsed eddy current testing and optimized Res2Net network. IEEE Trans. Instrum. Meas. p. 73, 1–13 (2024). https://doi.org/10.1109/TIM.2024.341810110.1109/TIM.2024.3418101 ↗
11. Meng, T., Tao, Y., Chen, Z., Salas, J.R., Avila, Q., Ran, Y., Shao, R., Huang, et al.: Depth evaluation for metal surface defects by eddy current testing using deep residual convolutional neural networks. IEEE Trans. Instrum. Meas. p. 70, 1–13 (2021). https://doi.org/10.1109/TIM.2021.311736710.1109/TIM.2021.3117367 ↗
12. Mohseni, E., Viens, M., Xie, W.-F.: Adaptive neuro-fuzzy inference system trained for sizing semi-elliptical notches scanned by eddy currents. J. Nondestr. Eval. p. 39, 1–12 (2020). https://doi.org/10.1007/s10921-019-0648-810.1007/s10921-019-0648-8 ↗
13. Smid, R., Docekal, A., Kreidl, M.: Automated classification of eddy current signatures during manual inspection, NDT&E International, vol. 38, no. 6, pp. 462–470, (2005). https://doi.org/10.1016/j.ndteint.2004.12.00410.1016/j.ndteint.2004.12.004 ↗
14. Bernieri, L., Ferrigno, M., Laracca, M., Molinara, M.: Crack shape reconstruction in eddy current testing using machine learning systems for regression. IEEE Trans. Instrum. Meas. p. 57(9), 1958–1968 (2008). https://doi.org/10.1109/TIM.2008.91901110.1109/TIM.2008.919011 ↗
15. Yin, L., Ye, B., Zhang, Z., Tao, Y., Xu, H., Avila J.R.S., Yin, W.: A novel feature extraction method of eddy current testing for defect detection based on machine learning. NDT E Int. p. 107, 102–108 (2019). https://doi.org/10.1016/j.ndteint.2019.04.00510.1016/j.ndteint.2019.04.005 ↗
16. Zhu, P., Cheng, Y., Banerjee, P., Tamburrino, A., Deng, Y.: A novel machine learning model for eddy current testing with uncertainty. NDT&E Int. p. 101, 104–112 (2019). https://doi.org/10.1016/j.ndteint.2018.09.01010.1016/j.ndteint.2018.09.010 ↗
17. Zheng, B., Su, J.W., Xie, Y., Miles, J., Wang, H., Gao, W., Xin, M., Lin, J.: An autonomous robot for shell and tube heat exchanger inspection. J. Field Robot. p. 39(8), 1165–1177 (2022)10.1002/rob.22102 ↗
18. Dutta, C., Sagar, S.P., Kumar, A., Bhushan, R., Kadu, S., Das, T.K.: An adaptive sampling protocol for real-time defect assessment using eddy current sensor and machine learning algorithm. IEEE Trans. Ind. Appl. p. 59(5), 4556–4564 (2023). https://doi.org/10.1109/TIA.2023.328478210.1109/TIA.2023.3284782 ↗
19. Ye, B., Huang, P., Fan, M., Gong, X., Hou, D., Zhang, G., Zhou, Z.: Automatic classification of eddy current signals based on kernel methods. Nondestructive Test. Evaluation. p. 24, 1–2 (2009). https://doi.org/10.1080/1058975080200259010.1080/10589750802002590 ↗
20. Falque, R., Vidal-Calleja, T., Miro, J.V.: Defect detection and segmentation framework for remote field eddy current sensor data. Sens. (Switzerland). p. 17(10), 2276 (2017). https://doi.org/10.3390/s1710227610.3390/s17102276 ↗
21. Breiman, L.: Random forests. Mach. Learn. p. 45, 5–32 (2001). https://doi.org/10.1023/A:101093340432410.1023/A:1010933404324 ↗
22. Pal, M.: Random forest classifier for remote sensing classification. Int. J. Remote Sens. p. 26(1), 217–222 (2005). https://doi.org/10.1080/0143116041233126969810.1080/01431160412331269698 ↗
23. Probst, P., Wright, M.N., Boulesteix, A.L.: Hyperparameters and tuning strategies for random forest, Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, vol. 9, no. 3, (2019). https://doi.org/10.1002/widm.130110.1002/widm.1301 ↗
24. Liaw, Wiener, M.: Classification and regression by random forest. R News, 2, 3, (2002)
25. Vargas-Lopez, O., Perez-Ramirez, C.A., Valtierra-Rodriguez, M., Yanez-Borjas, J.J., Amezquita-Sanchez, J.P.: An explainable machine learning approach based on statistical indexes and SVM for stress detection in automobile drivers using electromyographic signals. Sensors. p. 21(9) (2021). https://doi.org/10.3390/s2109315510.3390/s21093155 ↗
26. Bosch, A., Zisserman, Munoz, X.: Image classification using random forests and ferns, Proceedings of the IEEE 11th International Conference on Computer Vision, pp. 1–8, (2007)10.1109/ICCV.2007.4409066 ↗
27. Eddy current examination of nonferromagnetic heat exchanger tubing: ASME Sect. V, (2017). Article 8, ASME International (BPVC)
28. Muller, M.: Dynamic time warping. Inform. Retr. Music Motion (Springer). p. 69–84 (2007). https://doi.org/10.1007/978-3-540-74048-3_410.1007/978-3-540-74048-3_4 ↗
29. Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and Regression Trees, 1st edn. Chapman & Hall/CRC, London (1984). https://doi.org/10.1201/978131513947010.1201/9781315139470 ↗
30. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B.: Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. p. 12, 9–12 (2011)
31. Chawla N.V., Bowyer K.W., Hall L.O., Kegelmeyer W.P.: SMOTE: Synthetic minority over-sampling technique. J. Artif. Intell. Res. p. 16, 321–357 (2002). https://doi.org/10.1613/jair.95310.1613/jair.953 ↗
32. Syarif, A., Prugel-Bennett, Wills, G.: SVM parameter optimization using grid search and genetic algorithm to improve classification performance, TELKOMNIKA (Telecommunication Computing Electronics and Control), 14, 4, pp. 1502–1509, (2016)10.12928/telkomnika.v14i4.3956 ↗
33. Tsang, W., Kwok, J.T., Cheung, P.M., Cristianini, N.: Core vector machines: Fast SVM training on very large data sets. J. Mach. Learn. Res. p. 6(4), 363–392 (2005)
34. Takhirov, Z., Wang, J., Louis, M.S., Saligrama, V., Joshi, A.: Field of groves: An energy-efficient random forest, Submitted as work in progress to Distributed, Parallel, and Cluster Computing, (2017). https://doi.org/10.48550/arXiv.1704.0297810.48550/arXiv.1704.02978 ↗