Abstract
Transformers are prone to metal corrosion due to long-term exposure in the external environment. It is necessary to detect corrosion in time to prolong their service life-time. Detecting metal corrosion based on deep learning is becoming a feasible method at present. However, because of the irregularity and detachability of metal corrosion, traditional annotation approach results in such problems as ambiguity and uncertainty in the annotating process. Thus, a novel hierarchical annotation approach is proposed in this paper. The rationale for this initiative is as follows: traditional annotation approach has been used to annotate a large area covering the range of corrosion, as long as the area is visually continuous and adjacent to the corrosion that cannot be clearly divided. The annotation result is recorded as training set A; secondly, in the annotating boxes from the first step, the areas with obvious and relatively independent features are re-annotated to form the second level of nested annotation. The annotation result is recorded as training set B. Finally, Faster R-CNN and YOLOv5 models were trained by A, B training sets respectively in the experiment. It can be concluded that the detection performance with hierarchical annotation approach proved better than traditional annotation approach for Faster R-CNN and YOLOv5 models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Roberge, P.R.: Handbook of Corrosion Engineering. McGraw-Hill Education, New York (2019)
Roberge, P.R.: Corrosion Engineering. McGraw-Hill Education, New York (2008)
Dunn, W.L., Yacout, A.M.: Corrosion detection in aircraft by X-ray backscatter methods. Appl. Radiat. Isot. 53(4–5), 625–632 (2000)
Gao, T., Sun, H., Hong, Y., et al.: Hidden corrosion detection using laser ultrasonic guided waves with multi-frequency local wavenumber estimation. Ultrasonics 108, 106182 (2020)
Doshvarpassand, S., Wu, C., Wang, X.: An overview of corrosion defect characterization using active infrared thermography. Infrared Phys. Technol. 96, 366–389 (2019)
Wicker, M., Alduse, B.P., Jung, S.: Detection of hidden corrosion in metal roofing shingles utilizing infrared thermography. J. Build. Eng. 20, 201–207 (2018)
Dudziak, M.J., Chervonenkis, A.Y., Chinarov, V.: Nondestructive evaluation for crack, corrosion, and stress detection for metal assemblies and structures. In: Nondestructive Evaluation of Aging Aircraft, Airports, and Aerospace Hardware III. International Society for Optics and Photonics, vol. 3586, pp. 20–31 (1999)
LeCun, Y., Boser, B., Denker, J.S., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105 (2012)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1–9 (2015)
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Yao, Y., Yang, Y., Wang, Y., et al.: Artificial intelligence-based hull structural plate corrosion damage detection and recognition using convolutional neural network. Appl. Ocean Res. 90, 101823 (2019)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497 (2015)
Redmon, J., Divvala, S., Girshick, R., et al.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Jocher, G., Stoken, A., Borovec, J., et al.: ultralytics/yolov5: v3.1 - bug fixes and performance improvements (2020). https://doi.org/10.5281/zenodo.4154370
Sutskever, I., Martens, J., Dahl, G., et al.: On the importance of initialization and momentum in deep learning. In: International Conference on Machine Learning, pp. 1139–1147. PMLR (2013)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456. PMLR (2015)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: ICML (2010)
Acknowledgement
This work was partly supported by Open Research Fund from State Key Laboratory of Smart Grid Protection and Control, China, Rapid Support Project (61406190120) and the National Key R&D Program of China (2018YFC0830200).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Cao, Y. et al. (2021). Corrosion Detection in Transformers Based on Hierarchical Annotation. In: Sun, X., Zhang, X., Xia, Z., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2021. Lecture Notes in Computer Science(), vol 12736. Springer, Cham. https://doi.org/10.1007/978-3-030-78609-0_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-78609-0_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-78608-3
Online ISBN: 978-3-030-78609-0
eBook Packages: Computer ScienceComputer Science (R0)