Image analysis and CNN-based crack depth estimation using eddy current data
145 viewsDOI:
https://doi.org/10.54939/1859-1043.j.mst.96.2024.12-20Keywords:
Non-Destructive Evaluation; Eddy-current technique; Convolutional Neural Network; Data augmentation.Abstract
This study presents a comprehensive approach for crack depth estimation utilizing advanced image analysis techniques and a Convolutional Neural Network (CNN) model. The aim is to enhance accuracy and reliability in predicting crack depths, particularly for sub-millimeter cracks. The research addresses challenges arising from noise in images by employing a pre-processing technique and augmentation methods. The proposed method's effectiveness is showcased through its application to experimental crack data from diverse specimens. The outcomes exhibit a Mean Relative Error (MRE) of around 6%, indicating a high level of precision. These results affirm the potential of the methodology for real-world industrial applications. Additionally, the study explores the integration of eddy current image processing with CNN for Non-Destructive Evaluation (NDE) problems, offering a new approach for tiny surface-crack detection and characterization.
References
[1]. H. S. Munawar, A. W. Hammad, A. Haddad, C. A. P. Soares, and S. T. Waller, “Image-based crack detection methods: A review,” Infrastructures, vol. 6, no. 8, pp. 115-135, (2021). DOI: https://doi.org/10.3390/infrastructures6080115
[2]. N. Yusa, H. Huang, and K. Miya, “Numerical Evaluation of the Ill-posedness of Eddy Current Problems to Size Real Cracks”, NDT&E International, vol. 40, pp. 185-191, (2007). DOI: https://doi.org/10.1016/j.ndteint.2006.10.012
[3]. Z. Xia, R. Huang, Y. Shao, X. Bai, and W. Yin, “Estimation of defect depth on plates by eddy-current coil array”, Sensors and Actuators A: Physical, p. 115114, (2024). DOI: https://doi.org/10.1016/j.sna.2024.115114
[4]. Y. Liu et al., “Depth quantification of rolling contact fatigue crack using skewness of eddy current pulsed thermography in stationary and scanning modes”, NDT & E International, vol. 128, p. 102630, (2022). DOI: https://doi.org/10.1016/j.ndteint.2022.102630
[5]. R. Gansel, H. J. Maier, and S. Barton, “Detection and characterization of fatigue cracks in butt welds of offshore structures using the eddy current method”, Journal of Nondestructive Evaluation, Diagnostics and Prognostics of Engineering Systems, vol. 6, no. 2, p. 21001, (2023). DOI: https://doi.org/10.1115/1.4056313
[6]. M. Zergoug, G. Kamel, and S. Lebailia, “Characterization of the corrosion by eddy current,” EUROCORR, vol. 36, pp. 1-7, (2004).
[7]. D. C. Copley, “Eddy-current imaging for defect characterization”, in: Review of Progress in Quantitative Nondestructive Evaluation: Volume 2A, Springer, pp. 1527–1540, (1983). DOI: https://doi.org/10.1007/978-1-4613-3706-5_102
[8]. L. Xie, B. Gao, G. Tian, J. Tan, B. Feng, and Y. Yin, “Coupling pulse eddy current sensor for deeper defects NDT,” Sens. Actuators Phys., vol. 293, pp. 189–199, (2019). DOI: https://doi.org/10.1016/j.sna.2019.03.029
[9]. D. Kim, L. Udpa, and S. Udpa, “Remote field eddy current testing for detection of stress corrosion cracks in gas transmission pipelines,” Mater. Lett., vol. 58, no. 15, pp. 2102–2104, (2004). DOI: https://doi.org/10.1016/j.matlet.2004.01.006
[10]. S. Xie, Z. Duan, J. Li, Z. Tong, M. Tian, and Z. Chen, “A novel magnetic force transmission eddy current array probe and its application for nondestructive testing of defects in pipeline structures,” Sens. Actuators Phys., vol. 309, p. 112030, (2020). DOI: https://doi.org/10.1016/j.sna.2020.112030
[11]. Z. Chu, Z. Jiang, Z. Mao, Y. Shen, J. Gao, and S. Dong, “Low-power eddy current detection with 1-1 type magnetoelectric sensor for pipeline cracks monitoring,” Sens. Actuators Phys., vol. 318, p. 112496, (2021). DOI: https://doi.org/10.1016/j.sna.2020.112496
[12]. Z. Tong et al., “Quantitative mapping of depth profile of fatigue cracks using eddy current pulsed thermography assisted by PCA and 2D wavelet transformation,” Mech. Syst. Signal Process., vol. 175, p. 109139, (2022). DOI: https://doi.org/10.1016/j.ymssp.2022.109139
[13]. L. T. Cung, T. D. Dao, P. C. Nguyen, and T. D. Bui, “A model-based approach for estimation of the crack depth on a massive metal structure,” Meas. Control, vol. 51, no. 5–6, pp. 182–191, (2018). DOI: https://doi.org/10.1177/0020294018778314
[14]. T.-D. Bui, V.-D. Pham, and T.-L. Cung, “Multilayer perceptron neural network and eddy current technique for estimation of the crack depth on massive metal structures,” J. Mil. Sci. Technol., no. 77, pp. 3–12, (2022). DOI: https://doi.org/10.54939/1859-1043.j.mst.77.2022.3-12
[15]. E. Mohseni, D. R. França, M. Viens, W. F. Xie, and B. Xu, “Finite element modelling of a reflection differential split-D eddy current probe scanning surface notches,” J. Nondestruct. Eval., vol. 39, pp. 1–14, (2020). DOI: https://doi.org/10.1007/s10921-020-00673-6
[16]. M. Jesenik, V. Gorican, A. Hamler, and M. Trlep, “Finding a crack in a material and determining of depth,” IET 8th International Conference on Computation in Electromagnetics, 11-14 April, Wroclaw, pp. 1-2, (2011). DOI: https://doi.org/10.1049/cp.2011.0097
[17]. Z. Wang and Y. Yu, “Traditional eddy current–pulsed eddy current fusion diagnostic technique for multiple micro-cracks in metals,” Sensors, vol. 18, no. 9, p. 2909, (2018). DOI: https://doi.org/10.3390/s18092909
[18]. L. Tian, Y. Cheng, C. Yin, X. Huang, B. Zhang, and L. Bai, “Data-Driven Method for the Measurement of Thickness/Depth Using Pulsed Eddy Current.,” Sens. Mater., vol. 29, no. 9, pp. 1325-1338, (2017). DOI: https://doi.org/10.18494/SAM.2017.1610
[19]. F. Nafiah, A. Sophian, M. R. Khan, S. B. Abdul Hamid, and I. M. Zainal Abidin, “Image-based feature extraction technique for inclined crack quantification using pulsed eddy current,” Chin. J. Mech. Eng., vol. 32, no. 1, pp. 1–9, (2019). DOI: https://doi.org/10.1186/s10033-019-0341-y
[20]. M. Smetana, L. Behun, D. Gombarska, and L. Janousek, “New Proposal for Inverse Algorithm Enhancing Noise Robust Eddy-Current Non-Destructive Evaluation,” Sensors, vol. 20, no. 19, p. 5548, (2020). DOI: https://doi.org/10.3390/s20195548
[21]. T. Meng et al., “Depth evaluation for metal surface defects by eddy current testing using deep residual convolutional neural networks,” IEEE transactions on instrumentation and measurement, vol. 70, pp. 1–13, (2021). DOI: https://doi.org/10.1109/TIM.2021.3117367
[22]. Z. Zeng, Y. Li, L. Huang, and M. Luo, “Frequency-domain defect characterization in pulsed eddy current testing,” Int. J. Appl. Electromagn. Mech., vol. 45, no. 1–4, pp. 621–625, (2014). DOI: https://doi.org/10.3233/JAE-141885
[23]. T. Chen, G. Y. Tian, A. Sophian, and P. W. Que, “Feature extraction and selection for defect classification of pulsed eddy current NDT,” Ndt E Int., vol. 41, no. 6, pp. 467–476, (2008). DOI: https://doi.org/10.1016/j.ndteint.2008.02.002
[24]. R. Edwards, A. Sophian, S. Dixon, G.-Y. Tian, and X. Jian, “Dual EMAT and PEC non-contact probe: applications to defect testing,” NDT E Int., vol. 39, no. 1, pp. 45–52, (2006). DOI: https://doi.org/10.1016/j.ndteint.2005.06.001
[25]. G. Y. Tian and A. Sophian, “Defect classification using a new feature for pulsed eddy current sensors,” Ndt E Int., vol. 38, no. 1, pp. 77–82, (2005). DOI: https://doi.org/10.1016/j.ndteint.2004.06.001
[26]. M. Elad and M. Aharon, “Image denoising via sparse and redundant representations over learned dictionaries,” IEEE Trans. Image Process., vol. 15, no. 12, pp. 3736–3745, (2006). DOI: https://doi.org/10.1109/TIP.2006.881969
[27]. F. Chollet and others, “Keras.” 2015, [Online]. Available: https://keras.io.
[28]. C. R. Harris et al., “Array programming with NumPy,” Nature, vol. 585, no. 7825, pp. 357–362, (2020). DOI: https://doi.org/10.1038/s41586-020-2649-2
[29]. P. Virtanen et al., “SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python,” Nat. Methods, vol. 17, pp. 261–272, (2020).
