Education, Science, Technology, Innovation and Life
Open Access
Sign In

Defect Detection of Welding Spots on Steel Plate Surface Based on Improved Resnet Feature Extraction

Download as PDF

DOI: 10.23977/autml.2022.030303 | Downloads: 3 | Views: 83

Author(s)

Kang Sun 1, Shuchun Dong 1

Affiliation(s)

1 Dianrong Intelligent Technology Co., Ltd., Kunshan, 215334, China

Corresponding Author

Kang Sun

ABSTRACT

In order to deal with the problem of defect detection of welding spot on steel plate surface, an improved ResNet feature extraction method is proposed by embedding Squeeze and Excitation (SE) module, then the XGBoost classifier is combined to achieve reliable welding spot defect detection. The experimental results show that the proposed algorithm has achieved remarkable improvement in main indexes such as accuracy, precision and F1 score, the recall rate reaches 97%, which is of great significance for further industrial applications.

KEYWORDS

Welding spots, Detection of defects, ResNet, SE Module, Feature extraction

CITE THIS PAPER

Kang Sun, Shuchun Dong, Defect Detection of Welding Spots on Steel Plate Surface Based on Improved Resnet Feature Extraction. Automation and Machine Learning (2022) Vol. 3: 13-18. DOI: http://dx.doi.org/10.23977/autml.2022.030303.

REFERENCES

[1] YAN Meng, HUANG Huagui, YANG Zhiqiang, et al. Detection and analysis of head and tail plane shapes for aluminum alloy plate rough rolling based on machine vision. Journal of Plasticity Engineering, 2019, 26(3):257-261.
[2] Liu Han, Guo Runyuan. Detection and identification of SAWH pipe weld defects based on X-ray image and CNN. Chinese Journal of Scientific Instrument, 2018, 39(4):247-256.
[3] Daniel W, Bernd S R, Moshe S. Design of deep convolutional neural network architectures for automated feature extraction in industrial inspection. CIRP Annals, 2016, 65(1):417-420.
[4] Cha Y J, Choi W, Buyukozturk O. Deep learning-based crack damage detection using convolutional neural network. Computer-aided Civil & Infrastructure Engineering, 2017, 32(5):361-378.
[5] Frigo O, Sabater N, Delon J, et al. Split and match: example-based adaptive patch sampling for unsupervised style transfer. Proceedings of the Computer Vision and Pattern Recognition. IEEE, 2016:553-561. 
[6] Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. Proceeding of the International Conference on Neural Information Processing Systems. MIT Press, 2015:91-99.
[7] Nam H, Han B. Learning multi-domain convolutional neural networks for visual tracking. IEEE Conference on Computer Vision and Pattern Recognition, 2015:4293-4302.
[8] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition, 2016:770-778.
[9] Hu J, Shen L, Albanie S, et al. Squeeze-and-excitation networks. IEEE transactions on pattern analysis and machine intelligence, 2020, 42(8):2011-2023.
[10] Chen T, Gurstrin C. XGBoost: a scalable tree boosting system. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016:785-794.

Downloads: 254
Visits: 11362

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.