Bauman Moscow State Technical University (Moscow, Russia)

N. V. Krysko, Cand. Eng., Associate Prof., Dept. MT-7 “Welding Tehnology and Diagnostics”, e-mail: kryskonv@bmstu.ru
N. A. Shchipakov, Cand. Eng., Associate Prof., Dept. MT-7 “Welding Tehnology and Diagnostics”, e-mail: shchipak@bmstu.ru
D. M. Kozlov, Cand. Eng., Engineer, e-mail: kozlovdm@bmstu.ru
A. G. Kusyy, Engineer, e-mail: kusyy@bmstu.ru

In this work, a computer vision system is proposed, which allows the identification and localization of pitting corrosion on metallic surface of the gas pipelines made of low carbon and low alloy steels. For this purpose, a dataset of 5,760 images of pipeline surface with and without pitting corrosion was collected. The developed convolutional neural network (CNN) architecture was trained on this dataset. The hyperparameters of this architecture were optimized using Bayesian optimization. The developed and optimized CNN architecture does not have a large number of trainable parameters compared to existing CNN-based architectures. Also, the developed architecture showed significantly higher accuracy of 98.44 %, when classifying images into images without corrosion and with pitting corrosion. The developed CNN outperformed most existing classifiers in its parameters. A pitting corrosion localization system was also developed using the “sliding windows” and “image pyramid” methods, which made it possible to localize areas with identified pitting corrosion on the surface of pipelines made of low carbon and low alloy steels, using the developed CNN without additional labeling of the data set. The proposed deep learning approach will eliminate the need for the operator to visually inspect the pipeline for pitting corrosion, which is costly and time-consuming method.

The research was carried out with financial support of the grant of Russian Scientific Fund No. 22-29-00524, https://rscf.ru/project/22-29-00524/.

1. Davydova D. G. Defects of technological pipelines: typology, evaluation of the effect on operation. Prombezopasnost-Priuralye. 2012. No. 8. pp. 24-28.
2. Erekhinskiy B. A., Maslakov S. V., Shustov N. I., Mitrofanov A. V., Baryshev S. N., Zaryaev M. Yu., Kravtsov A. V., Egorov S. V. Metal cracking in Christmas-tree gate valves of gas producing wells in northern deposits. Territoriya Neftegaz. 2014. No. 2. pp. 31–36.
3. Safina I. S., Kauzova P. A., Gushchin D. A. Evaluation of technical state of vertical steel tanks. TekhNadzor. 2016. No. 3 (112). pp. 39–42.

4. Butusov D. S., Egorov S. I., Zavyalov A. P., Lyapichev D. M. Corrosion cracking of gas pipelines under stress: A manual. Мoscow: Izdatelskiy tsentr RGU nefti i gaza imeni I. M. Gubkina. 2015. 80 p.
5. Kalinichenko N. P., Vasilyeva M. A. Atlas of defects in welding joints and main metal: A manual. Tomsk: Izdatelstvo Tomskogo politekhnicheskogo universiteta. 2006. p. 55.
6. Aleshin N. P., Skrynnikov S. V., Krysko N. V., Shchipakov N. A., Kusyi A. G. Classification of surface defects in the main metal of pipelines based on the results of complex diagnostics. Kompyuternaya optika. 2023. Vol. 47. No. 1. pp. 170–178. DOI: 10.18287/2412-6179-CO-1185
7. Challa S., Koks D. Bayesian and Dempster-Shafer fusion. Sadhana. 2004. Vol. 29. pp. 145–176. DOI: 10.1007/BF02703729
8. Choi K.-Y, Kim S. Morphological analysis and classification of types of surface corrosion damage by digital image processing. Corrosion Science. 2005. Vol. 47 (1). pp. 1–15.
9. Medeiros F. N., Ramalho G. L., Bento M. P., Medeiros L. C. On the evaluation of texture and color features for nondestructive corrosion detection. EURASIP J. Appl. Signal Process. 2010. No. 1. 817473.
10. Khayatazad M., De Pue L., De Waele W. Detection of corrosion on steel structures using automated image processing. Developments in the Built Emvironment. 2020. No. 3. 100022.
11. Ortiz A., Bonnin-Pascual F., Garcia-Fidalgo E. et al. Visionbased corrosion detection assisted by a micro-aerial vehicle in a vessel inspection application. Sensors. 2016. Vol. 16 (12). 2118.
12. Ahuja S. K. Surface Corrosion Detection and Classification for Steel Alloy using Image Processing and Machine Learning. Helix. 2018. Vol. 8 (5). pp. 3822–3827.
13. Hoang N. D., Tran V. D. Image processing –based detection of pipe corrosion using texture analysis and metaheuristic-optimized machine learning approach. Hindwi. Computational Intellegence and Neuroscience. 2019. article ID 8097213. 13 p.
14. Krizhevsky A., Sutskever I., Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems. 2012. p. 1097–105.
15. Zeiler M. D., Fergus R. Visualizing and understanding convolutional networks. European conference on computer vision. Springer. 2014. pp. 818–833.
16. Simonyan K., Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. The 3^rd International Conference on Learning Representations (ICLR 2015). 2015. pp. 1–14.
17. Szegedy C., Vanhoucke V., Ioffe S., Shlens J., Wojna Z. Rethinking the Inception Architecture for Computer Vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA. 2016. pp. 2818–2826.
18. He K., Zhang X., Ren S., Sun J. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA. 2016. pp. 770–778.
19. Chollet F. Xception: Deep Learning with Depthwise Separable Convolutions. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA. 2017. pp. 1800–1807.
20. Golyak I. S., Kareva E. R., Fufurin I. L., Anfimov D. R., Scherbakova A. V., Nebritova A. O., Demkin P. P., Morozov A. N. Numerical methods of spectral analysis of multicomponent gas mixtures and human exhaled breath. Computer Optics. 2022. Vol. 46 (4). pp. 650–658. DOI: 10.18287/2412-6179-CO-1058
21. Wang L., Liu Y., Fu L., Wang Y., Tang N. Functional Intelligence-Based Scene Recognition Scheme for MAV Environment-Adaptive Navigation. Drones. 2022. No. 6. p. 120.
22. Fufurin I., Berezhanskiy P., Golyak I., Anfimov D., Kareva E., Scherbakova A., Demkin P., Nebritova O., Morozov. A. Deep Learning for Type 1 Diabetes Mellitus Diagnosis Using Infrared Quantum Cascade Laser Spectroscopy. Materials. 2022. No. 15. p. 2984.
23. Lobanova V., Slizov V., Anishchenko L. Contactless Fall Detection by Means of Multiple Bioradars and Transfer Learning. Sensors. 2022.,No. 22. p. 6285.
24. Bobkov A., Aung Kh. Real-Time Person Identification by Video Image Based on YOLOv2 and VGG 16 Networks. Automation and Remote Control. 2022. Vol. 83. No. 10. pp. 1567–1575.
25. Atha D. J., Jahanshahi M. R. Evaluation of deep learning approaches based on convolutional neural networks for corrosion detection. Struct. Health Monit. 2017. pp. 1110–1128.
26. Petricca L., Moss T., Figueroa G., Broen S. Corrosion detection using ai: a comparison of standard computer vision techniques and deep learning model. The Sixth International Conference on Computer Science, Engineering and Information Technology. 2016. pp. 91–99.
27. Ahuja S. K., Shukla M. K., Ravulakollu K. K. Surface corrosion grade classification using convolution neural network. IJRTE. 2019. Vol. 8. Iss. 3. September. pp. 7645–7649.
28. Bastiana B. T., Na J., Ranjithb S. K., Jijia C. V. Visual inspection and characterization of external corrosion in pipelines using deep neural network. NDT and E International. 2019. Vol. 107. 102134.
29. Katsamenis I., Protopapadakis E., Doulamis A., Doulamis N., Voulodimos A. Pixel-Level Corrosion Detection on Metal Constructions by Fusion of Deep Learning Semantic and Contour Segmentation. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2020. Lecture Notes in Computer Science. Springer, Cham. 2020. Vol. 12509. pp. 160–169.
30. Zhang S., Li Z., Yang C., Zhu C. Segmenting localized corrosion from rust-removed metallic surface with deep learning algorithm. Journal of Electronic Imaging. 2019. Vol. 28. Iss. 4 (July). 043019.
31. Min Lin, Qiang Chen, Shuicheng Yan. Network in network. ArXiv preprint arXiv. 2013. 1312.4400.
32. Dewancker I., McCourt M., Clark S. Bayesian optimization for machine learning: A practical guidebook. ArXiv. 2016. 1612.04858.
33. Ebden M. Gaussian Processes for Regression: A Quick Introduction. ArXiv. 2015. Vol. 2. 1505.02965.
34. Hutter F., Hoos H. H., Leyton-Brown K. Sequential modelbased optimization for general algorithm configuration. International conference on learning and intelligent optimization. 2011. pp. 507–523.
35. Bergstra J., Bardenet R., Bengio Y., Kégl B. Algorithms for hyperparameter optimization. In: Shawe-Taylo J., Zemel R. S., Bartlett P., Pereira F., Weinberger K. Q. (Eds.). 25^th Annual Conference on Neural Information Processing Systems, Granada (Spain), 12–15 December 2011. 2011. pp. 2546–2554.
36. Ioffe S., Szegedy C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. ICML’15: Proceedings of the 32^nd International Conference on International Conference on Machine Learning. 2015. July. Vol. 37. pp. 448–456.
37. Taner A., Öztekin Y. B., Duran H. Performance Analysis of Deep Learning CNN Models for Variety Classification in Hazelnut. Sustainability. 2021 Vol. 13. 6527.
38. Lowe D. G. Object recognition from local scale-invariant features. Computer vision, The proceedings of the seventh IEEE international conference 1999. 1999. pp. 1150–1157.
39. Felzenszwalb P., McAllester D., Ramanan D. A discriminatively trained, multiscale, deformable part model. Computer vision and pattern recognition. IEEE international conference 2008. 2008. pp. 1–8.
40. Liu W., Anguelov D., Erhan D., Szegedy C., Reed S., Fu C.-Y., Berg A. C. SSD: single shot multibox detector. European conference on computer vision. 2016. pp. 21–37.
41. Lin T.-Y., Dollár P., Girshick R., He K., Hariharan B., Belongie S. Feature pyramid networks for object detection. IEEE Conference on Computer Vision and Pattern Recognition. 2017. Vol. 1. pp. 2117–2125.
42. Ren S., He K., Girshick R., Sun J. Faster R-CNN: towards realtime object detection with region proposal networks. Advances in neural information processing systems. 2015. pp. 1137–1149.
43. Hosang J., Benenson R., Schiele B., Learning Non-maximum Suppression. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017. 2017. pp. 6469–6477.