Deep Learning-Based Classification of Weld Surface Defects
Source abstract
Abstract
In order to realize the non-destructive intelligent identification of weld surface defects, an intelligent recognition method based on deep learning is proposed, which is mainly formed by convolutional neural network (CNN) and forest random. First, the high-level features are automatically learned through the CNN. Random forest is trained with extracted high-level features to predict the classification results. Secondly, the weld surface defects images are collected and preprocessed by image enhancement and threshold segmentation. A database of weld surface defects is established using pre-processed images. Finally, comparative experiments are performed on the weld surface defects database. The results show that the accuracy of the method combined with CNN and random forest can reach 0.9875, and it also demonstrates the method is effective and practical.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Welding Techniques and Residual Stresses · Non-Destructive Testing Techniques · Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control, School of Mechanical Engineering, Tianjin University of Technology, Tianjin 300384, China
National Demonstration Center for Experimental Mechanical and Electrical Engineering Education, School of Mechanical Engineering, Tianjin University of Technology, Tianjin 300384, China
State Key Lab of Digital Manufacturing Equipment & Technology, School of Mechanical Science & Engineering, Huazhong University of Science & Technology, Wuhan 430074, China
Funding
the Tianjin Science and Technology Major Projects and Engineering Projects
References (34)
Show source-provided references
1. Weld defect detection using PPM EMAT generated shear horizontal ultrasound10.1016/j.ndteint.2015.05.005 ↗
2. Automatic weld defect detection method based on Kalman filtering for real-time radiographic inspection of spiral pipe10.1016/j.ndteint.2015.01.002 ↗
3. Elimination of coil liftoff from eddy current measurements of conductivity10.1109/TIM.2013.2272842 ↗
4. Mery, D., and Arteta, C. (2017, January 24–31). Automatic defect recognition in x-ray testing using computer vision. Proceedings of the IEEE Winter Conference on Applications of Computer Vision, Santa Rosa, CA, USA.10.1109/WACV.2017.119 ↗
5. Sun, J., Li, C., Wu, X.J., Palade, V., and Fang, W. (2019). An effective method of weld defect detection and classification based on machine vision. IEEE Trans. Ind. Inform.10.1109/TII.2019.2896357 ↗
6. Multiclass defect detection and classification in weld radiographic images using geometric and texture features10.1016/j.eswa.2010.04.082 ↗
7. Yin, Z.Y., Ye, B., and Zhang, Z.L. (2019). A novel feature extraction method of eddy current testing for defect detection based on machine learning. NDT E Int.10.1016/j.ndteint.2019.04.005 ↗
8. Automated detection of welding defects in pipelines from radiographic images DWDI10.1016/j.ndteint.2016.11.003 ↗
9. Performance evaluation of an automatic inspection system of weld defects in radiographic images based on neuro-classifiers10.1016/j.eswa.2011.01.092 ↗
10. Automatic weld defect identification from radiographic images10.1016/j.ndteint.2012.11.005 ↗
11. Weld defect classification based on texture features and principal component analysis10.1784/insi.2016.58.4.194 ↗
12. Automatic classification approach to weld defects based on PCA and SVM10.1784/insi.2012.55.10.535 ↗
13. Reducing the dimensionality of data with neural networks10.1126/science.1127647 ↗
14. ImageNet classification with deep convolutional neural networks
15. Deep learning10.1038/nature14539 ↗
16. Yang, N.N., Niu, H.J., Chen, L., and Mi, G.H. (2018). X-ray weld image classification using improved Convolutional Neural Network. AIP Conf. Proc., 1995.10.1063/1.5048766 ↗
17. Deep features based on a DCNN model for classifying imbalanced weld flaw types10.1016/j.measurement.2018.09.011 ↗
18. Khumaidi, A., Yuniarno, E.M., and Purnomo, M.H. (2017, January 28–29). Welding defect classification based on convolution neural network (CNN) and Gaussian kernel. Proceedings of the International Seminar on Intelligent Technology and Its Applications, Surabaya, Indonesia.10.1109/ISITIA.2017.8124091 ↗
19. Liu, B., Zhang, X.Y., Gao, Z.Y., and Chen, L. (2017, January 8–9). Weld defect images classification with VGG16-Based neural network. Proceedings of the International Forum on Digital TV and Wireless Multimedia Communications, Shanghai, China.10.1007/978-981-10-8108-8_20 ↗
20. Automatic detection of welding defects using deep neural network10.1088/1742-6596/933/1/012006 ↗
21. Du, W.Z., Shen, H.Y., Fu, J.Z., Zhang, G., and He, Q. (2019). Approaches for improvement of the X-ray image defect detection of automobile casting aluminum parts based on deep learning. NDT E Int., 107.10.1016/j.ndteint.2019.102144 ↗
22. Spectral–spatial multi-feature-based deep learning for hyperspectral remote sensing image classification10.1007/s00500-016-2246-3 ↗
23. Audio-visual speech recognition using deep learning10.1007/s10489-014-0629-7 ↗
24. Advances in natural language processing10.1126/science.aaa8685 ↗
25. Simonyan, K., and Zisserman, A. (2014, January 24–27). Very deep convolutional networks for large-scale image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.
26. Szegedy, C., Liu, W., Jia, Y.Q., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2014, January 24–27). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2015.7298594 ↗
27. A fast learning algorithm for deep belief nets10.1162/neco.2006.18.7.1527 ↗
28. Wang, F., Lee, N., Sun, J.M., Hu, J.Y., and Ebadollahi, S. (2011, January 7–11). Automatic group sparse coding. Proceedings of the AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.
29. Representational power of restricted Boltzmann machines and deep belief networks10.1162/neco.2008.04-07-510 ↗
30. Cai, Z.W., Fan, Q.F., Feris, R.S., and Vasconcelos, N. (2016, January 8–16). A unified multi-scale deep convolutional neural network for fast object detection. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46493-0_22 ↗
31. Lin, T.Y., Dollar, P., Girshick, R., He, K.M., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
32. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
33. Scherer, D., Müller, A., and Behnke, S. (2010, January 15–18). Evaluation of pooling operations in convolutional architectures for object recognition. Proceedings of the International Conference on Artificial Neural Networks, Thessaloniki, Greece.10.1007/978-3-642-15825-4_10 ↗
34. Random Forest10.1023/A:1010933404324 ↗