System Invariant Method for Ultrasonic Flaw Classification in Weldments Using Residual Neural Network
Source abstract
Abstract
The industrial use of ultrasonic flaw classification using neural networks in weldments must overcome many challenges. A major constraint is the use of numerous systems, including a combination of transducers and equipment. This causes high complexity in the datasets used in the training of neural networks, which decreases performance. In this study, the performance of a neural network was enhanced using signal processing on an ultrasonic weldment flaw dataset to achieve system invariance. The dataset contained 5839 ultrasonic flaw signals collected by various types of transducers connected to KrautKramer USN60. Every signal in the dataset was from 45 FlawTech/Sonaspection weldment specimens with five types of flaw: crack, lack of fusion, slag inclusion, porosity, and incomplete penetration. The neural network used in this study is a residual neural network with 19 layers. The performance evaluation of the same network structure showed that the original database can achieve 62.17% ± 4.13% accuracy, and that the invariant database using the system invariant method can achieve 91.45% ± 1.77% accuracy. The results demonstrate that using a system invariant method for ultrasonic flaw classification in weldments can improve the performance of a neural network with a highly complex dataset.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Welding Techniques and Residual Stresses · Non-Destructive Testing Techniques · Advanced Welding Techniques Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Mechanical Engineering, College of Engineering, Sungkyunkwan University, Suwon 16419, Korea
Korea Institute of Nuclear Safety, Daejeon 34142, Korea
References (35)
Show source-provided references
1. Ultrasonic flaw classification in weldments using probabilistic neural networks10.1007/BF00568290 ↗
2. Neural network classification of flaws detected by ultrasonic means10.1016/0963-8695(95)00053-4 ↗
3. Frequency invariant classification of ultrasonic weld inspection signals10.1109/58.677606 ↗
4. The use of neural networks in ultrasonic flaw detection10.1016/S0263-2241(98)00075-X ↗
5. Development of an intelligent system for ultrasonic flaw classification in weldments10.1016/S0029-5493(01)00495-2 ↗
6. Flexible decision support system for ultrasound evaluation of fiber–metal laminates implemented in a DSP10.1016/j.ndteint.2015.12.001 ↗
7. Efficient feature selection for neural network based detection of flaws in steel welded joints using ultrasound testing10.1016/j.ultras.2016.08.017 ↗
8. Ultrasonic signal classification and imaging system for composite materials via deep convolutional neural networks10.1016/j.neucom.2016.11.066 ↗
9. Investigation of deep neural network with drop out for ultrasonic flaw classification in weldments10.1007/s12206-018-0610-1 ↗
10. Convolutional neural network for ultrasonic weldment flaw classification in noisy conditions10.1016/j.ultras.2018.12.001 ↗
11. Performance enhancement of convolutional neural network for ultrasonic flaw classification by adopting autoencoder10.1016/j.ndteint.2020.102218 ↗
12. Rimoldi, B. (2016). Principles of Digital Communication: A Top-Down Approach, Cambridge University Press.10.1017/CBO9781316337387 ↗
13. Gallager, R.G. (2008). Principles of Digital Communication, Cambridge University Press.10.1017/CBO9780511813498 ↗
14. Rumelhart, D.E., Hinton, G.E., and Williams, R.J. (1985). Learning Internal Representations by Error Propagation, California University San Diego La Jolla Inst for Cognitive Science (ICS-8506).10.21236/ADA164453 ↗
15. Rosenblatt, F. (1961). Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms, Spartan Books.10.21236/AD0256582 ↗
16. Géron, A. (2017). Hands on Machine Learning with Scikit-Learn and Tensorflow: Concepts, Tools, and Techniques to Build Intelligent Systems, O’Reilly Media Inc.
17. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
18. Nielsen, M.A. (2015). Neural Networks and Deep Learning, Determination Press.
19. Li, F.F., Karpathy, A., Johnson, J., and Yeung, S. (CS231n: Convolutional Neural Networks for Visual Recognition, 2016). CS231n: Convolutional Neural Networks for Visual Recognition.
20. Gradient-based Learning Applied to Document Recognition10.1109/5.726791 ↗
21. Deep learning10.1038/nature14539 ↗
22. Springenberg, J.T., Dosovitskiy, A., Brox, T., and Riedmiller, M. (arXiv, 2014). Striving for simplicity: The all convolutional net, arXiv.
23. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
24. Krizhevsky, A., and Hinton, G. (2009). Learning Multiple Layers of Features from Tiny Images, Computer Science Department, University of Toronto. Available online: https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf.
25. Deep residual learning for image steganalysis10.1007/s11042-017-4440-4 ↗
26. Development of a deep residual learning algorithm to screen for glaucoma from fundus photography10.1038/s41598-018-33013-w ↗
27. Pest identification via deep residual learning in complex background10.1016/j.compag.2017.08.005 ↗
28. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load10.1016/j.ymssp.2017.06.022 ↗
29. Nair, V., and Hinton, G.E. (2010, January 21–24). Rectified linear units improve restricted Boltzmann machines. Proceedings of the 27th International Conference on Machine Learning (ICML-10), Haifa, Israel.
30. Rectifier nonlinearities improve neural network acoustic models
31. Imagenet classification with deep convolutional neural networks10.1145/3065386 ↗
32. Kingma, D.P., and Ba, J. (arXiv, 2014). Adam: A method for stochastic optimization, arXiv.
33. Schmerr, L.W. (2016). Fundamentals of Ultrasonic Nondestructive Evaluation, Springer.10.1007/978-3-319-30463-2 ↗
34. McGillem, C.D., and Cooper, G.R. (1984). Continuous and Discrete Signal and System Analysis, Holt, Rinehart & Winston. [2nd ed.].
35. Weisstein, E.W. (2022, January 11). Convolution Theorem. From MathWorld—A Wolfram Web Resource. Available online: https://mathworld.wolfram.com/ConvolutionTheorem.html.