The Detection of Spark Scattering in the Slab Cutting Process Through Deep SVDD Based on Weakly Supervised Learning

被引：0

作者：

Kim S.-U. ^{[1
]}

Paik J.-H. ^{[1
]}

Kim S.-S. ^{[1
]}

Park J.-H. ^{[2
]}

Lee J.-W. ^{[3
]}

机构：

[1] AI Technology Group, POSCO ICT

[2] Production Technology Department, POSCO

[3] Department of Industrial Engineering, Chonnam National University

来源：

Journal of Institute of Control, Robotics and Systems | 2022年 / 28卷 / 05期

关键词：

Anomaly Detection; Deep SVDD; Multiple Instance Learning; Slab Cutting; Weakly Supervised Learning;

D O I：

10.5302/J.ICROS.2022.22.0030

中图分类号：

学科分类号：

摘要：

In the continuous casting process, which is one of the steel manufacturing processes, a slab is cut by a torch cutter. During cutting, sparks are generated around the slab; if a problem occurs, the sparks are scattered. The failure in recognizing this problem early on can lead to huge losses and serious accidents. Using learning-based network model, this paper proposes a method of spark scattering detection that can be used in the steel manufacturing process. However, since the spark scattering occurs very intermittently, it becomes difficult to secure sufficient data for network learning. To resolve this issue, this study uses an anomaly detection method through Deep SVDD. This study also applies a weakly supervised learning framework using a small amount of spark scattering data so that the network can extract discriminative features for normal and abnormal situations. © ICROS 2022.

引用

页码：514 / 519

页数：5

共 17 条

[1]

Yun J.P., Jung D.W., Park C.H., Surface defect in-spection system for hot slabs, Journal of Institute of Control, Robotics and Systems, 22, 8, pp. 627-632, (2016)

[2]

Scholkopf B., Platt J.C., Shawe J.T., Smola A.J., Williamson R.C., Estimation the support of a high-dimen-sional Distribution, Neural Computation, 13, 7, pp. 1443-1471, (2001)

[3]

Tax D.M.J., Duin R.P.W., Support vector data descrip-tion, Machine Learning, 54, 1, pp. 45-66, (2004)

[4]

Ruff L., Vandermeulen R., Gornitz N., Deeckesiddiqui L.S., Binder A., Muller E., Kloft M., Deep one-class classification, International Conference on Machine Learning, PMLR, (2018)

[5]

Schlegl T., Seebock P., Waldstein S.M., Schmidt-Erfurth U., Langs G., Unsupervised anomaly detection with generative adversarial networks to guide marker dis-covery, International Processing in Medical Imaging, (2017)

[6]

Goodfellow I., Pouget-Abadie J., Mirza M., Xu B., Warde-Farley D., Ozair S., Courville A., Bengio Y., Generative adversarial nets, Advances in Neural Information Processing Systems, 27, (2014)

[7]

Han H.G., Kim H.Y., Cho J.S., Cylindrical secondary battery defect detection method based on unsupervised deep-learning, Journal of Institute of Control, Robotics and Systems, 27, 8, pp. 510-517, (2021)

[8]

Lukas B.D., Kanade T., An iterative image registra-tion technique with an application to stereo, Proceedings of the 7Th International Joint Conference on Artificial Intel-Ligence (IJCAI '81), (1981)

[9]

Nguyen T.N., Meunier J., Anomaly detection in video sequence with appearance-motion correspondence, Proceedings of the IEEE/CVF International Conference on Computer, (2019)

[10]

Ravanbakhsh M., Nabi M., Sangineto E., Marcenaro L., Regazzoni C., Sebe N., Abnormal event detection in videos using generative adversarial nets, 2017 IEEE International Conference on Image Processing (ICIP), IEEE, (2017)

← 1 2 →