METAL FRACTURE IMAGE ANALYSIS FOR AUTOMATED STRENGTH MEASUREMENT BY THE VISCOSITY AREA SHARE

Vasilii Oskolkov; Egor Volkov; Olga   Salnikova; Evgeny Ershov

doi:10.59957/jctm.v60.i4.2025.16

Authors

Vasilii Oskolkov Michailovich
Egor Volkov
Olga Salnikova Department of Mathematic Software of Computing Machines, Cherepovets State University Cherepovets, Lunacharsky str. 5, Russia
Evgeny Ershov Department of Mathematic Software of Computing Machines, Cherepovets State University Cherepovets, Lunacharsky str. 5, Russia

DOI:

https://doi.org/10.59957/jctm.v60.i4.2025.16

Keywords:

viscosity area, brittle area, metal fracture, image analysis, neural network, quality control

Abstract

The article proposes an approach to the automated detection of the viscosity area share in a metal fracture by means of using its image, which can be used in various lighting and does not require special personnel training. The viscosity area share is determined by means of using a set of segmentation neural networks, which includes the U-NET, which finds the objects under test in the image, which are metal fractures, and the Mask R-CNN, which finds the brittle fracture areas. Neural networks were trained on a dataset provided by the customer. Experimental verification of the proposed solution confirmed the possibility of automating the process of measuring the strength properties of the metal from fracture images with an accuracy of at least 85 %.

Author Biography

Egor Volkov

Department of Mathematic Software of Computing Machines, Cherepovets State University

Cherepovets, Lunacharsky str. 5, Russia

References

API RP 5L3. Drop-Weight Tear Tests on Line Pipe, American Petroleum Institute, 2014, 11.

GOST 30456-2021. Metal products. Steel pipes, flat products and coiled products. Drop-Weight Impact Bending Test, Moscow: FSBI “Russian Standardization Institute”, 2022, 16.

Liu, H (Liu, Hui) Wang, B (Wang, Bin) Xiong, X (Xiong, Xin) Basic oxygen furnace steelmaking end-point prediction based on computer vision and general regression neural network, OPTIK. 2014. https://doi.org/10.1016/j.ijleo.2014.05.004

Mensik, M (Mensik, Martin) Spackova, H (Spackova, Hana) Slacala, J (Slacala, Jaroslav) Brezina, J (Brezina, Jan), The usage of machine vision in hot strip rolling processes, 28th International conference on metallurgy and materials (Metal 2019). https://doi.org/10.37904/metal.2019.783

Duchacek, J (Duchacek, Jan) Heger, M (Heger, Milan) Zimny, O (Zimny, Ondrej) Meca, R (Meca, Roman) Spicka, I (Spicka, Ivo), Options for measuring parameters of surfaces in metallurgy with exploitation of optical methods, Metal 2014: 23rd International conference on metallurgy and materials.

Fang X., Luo Q., Zhou B., Li C., Tian L, Research progress of automated visual surface defect detection for industrial metal planar materials, Sensors (Switzerland), 2020, 1-35. https://doi.org/10.3390/s20185136

Maohua Xiao, Weichen Wang, XiaojieShen, Yue Zhu, PetrBartos, YilidaerYiliyas, Research on defect detection method of powder metallurgy gear based on machine vision, Machine Vision and Applications, 2021. https://doi.org/10.1007/s00138-021-01177-7

Yun J.P., Shin W.C., Koo G., Kim M.S., Lee C., Lee S.J, Automated defect inspection system for metal surfaces based on deep learning and data augmentation, Journal of Manufacturing Systems, 2020, 317-324. https://doi.org/10.1016/j.jmsy.2020.03.009

Yun J.P., Kim D., Kim K., Lee S.J., Park C.H., Kim S.W, Vision-based surface defect inspection for thick steel plates, Optical Engineering, 56, 5, 2017. https://doi.org/10.1117/1.OE.56.5.053108

Liu Z., Hu J., Hu L., Zhang X., Kong J., Research on on-line surface defect detection for steel strip based on sparse coding, Advanced Materials Research, 2012, 749-752. https://doi.org/10.4028/www.scientific.net/AMR.548.749

Choi D.-C., Jeon Y.-J., Kim S.W, Faulty scarfing slab detection using machine vision // Advanced Materials Research, 2012, 185-190. https://doi.org/10.4028/www.scientific.net/AMR.462.185

Chen Y., Chen L., Liu X., Ding S., Zhang H, Real-time steel inspection system based on support vector machine and multiple kernel learning, Advances in Intelligent and Soft Computing. 2011, 185-190. https://doi.org/10.1007/978-3-642-25658-5_21

Xue B., Wu Z, Key Technologies of Steel Plate Surface Defect Detection System Based on Artificial Intelligence Machine Vision, Wireless Communications and Mobile Computing, 2021. https://doi.org/10.1155/2021/5553470

Weng Lilian, Object Recognition for Dummies Part 2: CNN, DPM and Overfeat. https://lilianweng. github.io/lil-log/2017/12/15/object-recognition-for-dummies-part-2.html.

Weng Lilian, Object Detection for Dummies Part 3, R-CNN Family. https://lilianweng.github.io/posts/2017-12-31-object-recognition-part-3/