Abstract
With the further development of industry, strip steel occupies an important position in industrial production and is widely used in various manufacturing fields. It is especially important to monitor the quality of strip steel production. In order to improve the detection rate of defective strip steel for its complex and varied surface defects and other characteristics, this paper proposes a defect classification algorithm based on the SFN-VIT (Improved Shuffle Network Unite Vision Transformer) model to classify six types of defects in strip steel and compare it with other classification algorithms based on convolutional neural network. The experimental data show that the proposed SFN-VIT model outperforms the traditional machine learning algorithm model and achieves an average accuracy of 91.7% for defect classification on the NEU-CLS dataset (Tohoku University strip steel surface defect categories dataset), which is a 5.1% improvement compared to the traditional classification algorithm.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Tang, M., Li, Y., Yao, W., Hou, L., Sun, Q., Chen, J.: A strip steel surface defect detection method based on attention mechanism and multi-scale maxpooling. Measure. Sci. Technol. 32(11), 115401 (2021)
Wang, W., et al.: Surface defects classification of hot rolled strip based on improved convolutional neural network: instrumentation, control and system engineering. ISIJ Int. 61(5), 1579–1583 (2021)
Support Vector Machines; New Support Vector Machines Study Findings Have Been Reported from University of Science and Technology (Multi-class classification method for strip steel surface defects based on support vector machine with adjustable hyper-sphere). J. Robot. Mach. Learn. (2019)
Di, H., Ke, Z., Peng, Z., Dongdong, Z.: Surface defect classification of steels with a new semi-supervised learning method. Optics Lasers Eng. 117, 40–48 (2019)
Jiaqiao, Z.: Surface defect detection of steel strips based on classification priority YOLOv3-dense network. Ironmaking Steelmaking 48, 547–558 (2020)
Moon, C.I., Choi, S.H., Kim, G.B., et al.: Classification of surface defects on cold rolled strip by tree-structured neural networks. Trans. Korean Soc. Mech. Eng. A 31(6), 651–658 (2007)
Luo, Q., Sun, Y., Li, P., et al.: Generalized completed local binary patterns for time-efficient steel surface defect classification. IEEE Trans. Instrum. Measure. 68(3), 667–679 (2018)
Hu, H., Li, Y., Liu, M., et al.: Classification of defects in steel strip surface based on multiclass support vector machine. Multimedia Tools Appl. 69(1), 199–216 (2014)
Wan, X., Zhang, X., Liu, L.: An improved VGG19 transfer learning strip steel surface defect recognition deep neural network based on few samples and imbalanced datasets. Appl. Sci. 11(6), 2606 (2021)
Dongyan, C., Kewen, X., Aslam, N., Jingzhong, H.: Defect classification recognition on strip steel surface using second-order cone programming-relevance vector machine algorithm. J. Comput. Theor. Nanosci. 13(9), 6141–6148 (2016)
Classification of surface defects of hot rolled strips: effectiveness of SVM over HOG and combined features GLCM. Int. J. Innov. Technol. Explor. Eng. 9(3) (2020)
Engineering; Researchers at Central South University Target Engineering (Surface defect classification for hot-rolled steel strips by selectively dominant local binary patterns). J. Eng. (2019)
Wang, C., Liu, Y., Yang, Y., Xu, X., Zhang, T.: Research on classification of surface defects of hot-rolled steel strip based on deep learning. In: Proceedings of 2019 2nd International Conference on Informatics, Control and Automation (ICA 2019), pp. 375–379 (2019)
Science - Science and Engineering; Investigators at University of Putra Malaysia Report Findings in Science and Engineering (Surface defects classification of hot-rolled steel strips using multi-directional Shearlet features). J. Eng. (2019)
Ashour, M.W., Khalid, F., Halin, A.A., Abdullah, L.N., Darwish, S.H.: Surface defects classification of hot-rolled steel strips using multi-directional Shearlet features. Arab. J. Sci. Eng. 44(4), 2925–2932 (2019)
Luo, Q., et al.: Surface defect classification for hot-rolled steel strips by selectively dominant local binary patterns. IEEE Access 7, 23488–23499 (2019)
Brendan, K., Isaac, H., Farhana, Z.: Condition-CNN: A hierarchical multi-label fashion image classification model. Expert Syst. Appl. 182, 11595 (2021)
Acknowledgements
This work was supported by the National Natural Science Foundation of China (61806088), by the Natural science fund for colleges and universities in Jiangsu Province (20KJA520007), by Graduate Practice Innovation Project Fund for Jiangsu university of Technology (XSJCX21_51).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 IFIP International Federation for Information Processing
About this paper
Cite this paper
Xing, L., Li, T., Fan, H., Zhu, H. (2022). Defect Detection and Classification of Strip Steel Based on Improved VIT Model. In: Shi, Z., Zucker, JD., An, B. (eds) Intelligent Information Processing XI. IIP 2022. IFIP Advances in Information and Communication Technology, vol 643. Springer, Cham. https://doi.org/10.1007/978-3-031-03948-5_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-03948-5_26
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-03947-8
Online ISBN: 978-3-031-03948-5
eBook Packages: Computer ScienceComputer Science (R0)
