Abstract
A deep neural network is expected to be a useful tool to improve the accuracy of defect detection in Non-Destructive Testing (NDT). In this article, a deep neural network-based technique to improve the defect detection accuracy of an advanced NDT using imaging the distribution of time-varying magnetic flux density (hereinafter, magnetic image) was investigated. Although deep neural networks require training on large amounts of data to achieve high performance, it is not easy to obtain large amounts of useful training data from many magnetic image-based NDT sites. So, we explored a way to improve the defect detection accuracy even with a limited amount of training data by mapping the widely scattered defect information into a specific region. In this article, a deep neural network for magnetic image-based NDT was trained using transformed images in which the alternating current (AC) components of the magnetic image signal were preserved and the direct current (DC) offset values were matched to a single reference value. Here, the defect information is mainly contained in the AC components. Experiments demonstrated that the deep neural network trained using transformed images significantly improved defect detection accuracy compared to the conventional deep neural network trained on images without transformation.
Similar content being viewed by others
REFERENCES
Sadek, H. M., NDE technologies for the examination of heat exchangers and boiler tubes—Principles, advantages and limitations, Insight, 2006, vol. 48, no. 3, pp. 181–183.
Gholizadeh, S., A review of non-destructive testing methods of composite materials, Procedia Struct. Integrity, 2016, vol. 1, pp. 50–57.
Lee, J., Nondestructive testing of train wheels using vertical magnetization and differential-type hall sensor array, IEEE Trans. Instrum. Meas., 2012, vol. 61, no. 9, pp. 2346–2353.
Kim, J., Jun, J., Lee, J., and Lee, J., An application of a magnetic camera for an NDT system for aging aircraft, J. Kor. Soc. Nondestr. Test., 2010, vol. 30, no. 3, pp. 212–224.
Hwang, J., Kim, J., and Lee, J., Magnetic images of surface crack on heated specimen using an area-type magnetic camera with high spatial resolution, Int. Instrum. Meas. Technol. Conf. (Singapore, 2009).
Sharatchandra, W., Rao, B.P.C., Vaidyanathan, S., Jayakumar, T., and Baldev, Raj., Detection of leakage magnetic flux from near-side and far-side defects in carbon steel plates using a giant magneto-resistive sensor, Meas. Sci. Technol., 2008, vol. 19, p. 015702.
Allweins, K., von Kreutzbruck, M., and Gierelt., G, Defect detection in aluminum laser welds using an anisotropic magneto-resistive sensor array, J. Appl. Phys., 2005, vol. 97, p. 10Q102.
Jun, J., Lee, J., Kim, J., Le, M., and Lee, S., Eddy current imager based on bobbin-type hall sensor arrays for nondestructive evaluation in small-bore piping system, Rev. Prog. Quant Nondest. Eval., 2012, vol. 32, pp. 502–509.
LeCun, Y., Bengio, Y., and Hinton, G., Deep learning, Nature, 2015, vol. 521, pp. 436–444.
Bernieri, A., Ferrigno, L., Laracca, M., and Molinara, M., Crack shape reconstruction in eddy current testing using machine learning systems for regression, IEEE Trans. Instrum. Meas., 2008, vol. 57, no. 9, pp. 1958–1968.
Xie, X., A review of recent advances in surface defect detection using texture analysis techniques, Electron. Lett. Comput. Vis. Image Anal., 2008, vol. 7, no. 3, pp. 1–22.
LeCun, Y., and Bengio, Y., Word-level training of a handwritten word recognizer based on convolutional neural networks, Proc. Int. Conf. Pattern Recognit. (Jerusalem, 1994).
Vilar, R., Zapata, J., and Ruiz, R., An automatic system of classification of weld defects in radiographic images, NDT & E Int., 2009, vol. 42, no. 5, pp. 467–476.
Boaretto, N. and Centeno, T., Automated detection of welding defects in pipelines from radiographic images DWDI, NDT & E Int., 2017, vol. 86, pp. 7–13.
Callet, P.Le., Barba, D., and Viard-Gaudin, C., A convolutional neural network approach for objective video quality assessment, IEEE Trans. Neural Networks, 2006, vol. 17, no. 5, pp. 1316–1327.
Krizhevskii, A., Sutskever, H., and Hinton, G., ImageNet classification with deep convolutional neural networks, Adv. Neural Inform. Proc. Syst., 2012, vol. 25.
Zeiler, M.D. and Fergus, R., Visualizing and understanding convolutional networks, Comput. Vision Pattern Recognit., 2013. arXiv:1311.2901[cs.CV].
Simonyan, K. and Zisserman, A., Very deep convolutional networks for large scale image recognition, Comput. Vision Pattern Recognit., 2015. arXiv:1409.1556v6[cs.CV].
He, K., Zhang, X., Ren, S., and Sun, J., Deep residual learning for image recognition, Comput. Vision Pattern Recognit., 2015. arXiv:1512.03385(cs).
Kappeler, A., Yoo, S., Dai, Q., and Katsaggelos, A. K., Video superresolution with convolutional neural networks, IEEE Trans. Comput. Imag., 2016, vol. 2, no. 2, pp. 109–122.
Mao, Q., Dong, M., Huang, Z., and Zhan, Y., Learning salient features for speech emotion recognition using convolutional neural networks, IEEE Trans. Multimedia, 2014, vol. 16, no. 8, pp. 2203–2213.
Swietojanski, P., Ghoshal, A., and Renals, S., Convolutional neural networks for distant speech recognition, IEEE Signal Process. Lett., 2014, vol. 21, no. 9, pp. 1120–1124.
He, K., Zhang, X., Ren, S., and Sun, J., Spatial pyramid pooling in deep convolutional networks for visual recognition, IEEE Trans. Pattern Anal. Mach. Intell., 2015, vol. 37, no. 9, pp. 1904–1916.
Chen, Y., Jiang, H., Li, C., Jia, X., and Ghamisi, P., Deep feature extraction and classification of hyperspectral images based on convolutional neural networks, IEEE Trans. Geosci. Remote Sens., 2016, vol. 54, no. 10, pp. 6232–6251.
Ting, P., Kasam, A., and Lan, K., Applications of convolutional neural networks in chest X-ray analyses for the detection of COVID-19, Ann. Biomed. Sci. Eng., 2022, vol. 6, pp. 1–7.
Akcay, S., Kundegorski, M.E., Willcocks, C.G., and Breckon, T.P., Using deep convolutional neural network architectures for object classification and detection within X-ray baggage security imagery, IEEE Trans. Inform. Forensics Secur., 2018, vol. 13, no. 9, pp. 2203–2215. https://doi.org/10.1109/TIFS.2018.2812196
Lu, S., Wang, S.H., and Zhang, Y.D., Detecting pathological brain via ResNet and randomized neural networks, Heliyon, 2020, vol. 6, no. 12. https://doi.org/10.1016/j.heliyon.2020.e05625
Salman, A., Siddiqui, S.A., Shafait, F., Mian, A., et al., Automatic fish detection in underwater videos by a deep neural network-based hybrid motion learning system, ICES J. Marine Sci., 2020, vol. 77, no. 4, pp. 1295–1307. https://doi.org/10.1093/icesjms/fsz025
Zhao, Z.Q., Zheng, P., Xu, S.T., and Wu, X., Object detection with deep learning: a review, IEEE Trans. Neural Networks Learn. Syst., 2019, vol. 30, no. 11, pp. 3212–3232. https://doi.org/10.1109//TNNLS.2018.2876865
Lundervold, A.S. and Lundervold A., An overview of deep learning in medical imaging focusing on MRI, Z. Med. Phys., 2019, vol. 29, no. 2, pp. 102–127. https://doi.org/10.1016/j.zemedi.2018.11.002
van Dyck, L.E., Kwitt, R., Denzler, S.J., and Gruber, W.R., Comparing object recognition in humans and deep convolutional neural networks-an eye tracking study, Front. Neurosci., 2021. https://doi.org/10.3389/fnins.2021.750639
Cui, X., Liu, Y., Zhang, Y., and Wang, C., Tire defects classification with multi-contrast convolutional neural networks, Int. J. Pattern. Recogn. Artif. Intell., 2018, vol. 32, no. 4, pp. 1056–1066.
Sammons, D., Winfree, W., Burke, E., and Ji, S., Segmenting delaminations in carbon fiber reinforced polymer composite CT using convolutional neural networks, AIP Conf. Proc., 2016, vol. 1706, p. 110014. https://doi.org/10.1063/1.4940585
Faghih-Roohi, S., Hajizadeh, S., Nez, A., Babuska, R., and Schutter, B., Deep convolutional neural networks for detection of rail surface defects, Int. Joint Conf. Neural Networks (Vancouver, 2016). https://doi.org/10.1109/IJCNN.2016.7727522
Feng, J., Li, F., Lu, S., Liu, J., and Ma, D., Injurious or noninjurious defect identification from MFL images in pipeline inspection using convolutional neural network, IEEE Trans. Instrum. Meas., 2017, vol. 66, no. 7, pp. 1883–1892.
Zhua, P., Cheng, Y., Banerjee, P., Tamburrino, A., and Deng Y., A novel machine learning model for eddy current testing with uncertainty, NDT & E Int., 2019, vol. 101, pp. 104–112.
ACKNOWLEDGMENTS
This work was supported by the Korea Atomic Energy Research Institute (KAERI), granted by the Korean government (project no. 524430-22).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare that they have no conflicts of interest.
Rights and permissions
About this article
Cite this article
Park, SK., Kim, J., Park, DG. et al. Experimental Investigation to Improve Inspection Accuracy of Magnetic Field Imaging-Based NDT Using Deep Neural Network. Russ J Nondestruct Test 58, 732–744 (2022). https://doi.org/10.1134/S1061830922080101
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1061830922080101