A Deep Learning-Based Ultrasonic Diffraction Data Analysis Method for Accurate Automatic Crack Sizing
Source abstract
Abstract
The purpose of this paper is to automate the interpretation of data during ultrasonic diffraction using a non-destructive testing (NDT) technique to accurately size defects for assisting in decision-making. A convolutional neural network (CNN) architecture was developed to automatically measure the length of the defect. Using the architecture, the population of A-scan signals in the scanning path was classified. The defect region was extracted and its size in the scanning direction was obtained by the connected region solution algorithm based on the classification results. The arrival time of diffraction waves was accurately identified by the intelligent denoising framework proposed, combined with Hilbert transform, and then the height of defects was calculated by corresponding geometric relations. The estimation results demonstrate that the measurement method can be considered as a useful technique for crack sizing in industrial structures, even in the case of complex noise.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Ultrasonics and Acoustic Wave Propagation · Non-Destructive Testing Techniques · Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Material Science and Engineering, Southeast University, Nanjing 211189, China
School of Power and Mechanical Engineering, Wuhan University, Wuhan 430072, China
Funding
National Key Research and Development Project of China
References (35)
Show source-provided references
1. Interpretation of TOFD data in the light of ASME XI and similar rules
2. Defect sizing using an ultrasonic time delay approach
3. Defect detection of spherical heads by time-of-flight diffraction10.1016/j.apacoust.2023.109787 ↗
4. The potential of scattered or diffracted ultrasound in the determination of crack depth10.1016/0029-1021(75)90024-9 ↗
5. Modified ultrasonic time-of-flight diffraction testing with Barker code excitation for sizing inclined crack10.1016/j.apacoust.2018.05.023 ↗
6. Reliability of non-destructive test techniques in the inspection of pipelines used in the oil industry10.1016/j.ijpvp.2008.05.001 ↗
7. Bolland, P., Voon, L.L., Gremillet, B., Pillet, L., Diou, A., and Gorria, P. (1996, January 18). The application of Hough transform on ultrasonic images for the detection and characterization of defects in non-destructive inspection. Proceedings of the Third International Conference on Signal Processing (ICSP’96), Beijing, China.
8. Mathematical morphology for TOFD image analysis and automatic crack detection10.1016/j.ultras.2014.03.005 ↗
9. Bolland, P., Voon, L.L., Gorria, P., Gremillet, B., and Pillet, L. (1997, January 20). Gradient-based Hough transform for the detection and characterization of defects during non-destructive inspection. Proceedings of the IEEE/ASME International Conference on Advanced Intelligent Mechatronics, Tokyo, Japan.
10. Towards automatic analysis of ultrasonic time-of-flight diffraction data using genetic-based Inverse Hough Transform10.1784/insi.2009.51.4.184 ↗
11. Parabola detection using matched filtering for ultrasound B-scans10.1016/j.ultras.2011.07.006 ↗
12. Ultrasonic distance and velocity measurement using a pair of LPM signals for cross-correlation method: Improvement of Doppler-shift compensation and examination of Doppler velocity estimation10.1016/j.ultras.2012.02.007 ↗
13. Cross-Correlation and Sine-Fitting Techniques for High Resolution Ultrasonic Ranging10.1109/IMTC.2006.328588 ↗
14. Model-based estimation of ultrasonic echoes. Part I: Analysis and algorithms10.1109/58.920713 ↗
15. Model-based estimation of ultrasonic echoes. Part II: Nondestructive evaluation applications10.1109/58.920714 ↗
16. New matching pursuit-based algorithm for SNR improvement in ultrasonic NDT
17. Accurate ultrasonic measurement technique for crack sizing using envelope detection and differential evolution
18. An end-to-end welding defect detection approach based on titanium alloy time-of-flight diffraction images10.1007/s10845-021-01905-w ↗
19. DefectDet: A deep learning architecture for detection of defects with extreme aspect ratios in ultrasonic images10.1016/j.neucom.2021.12.008 ↗
20. Sizing of flaws using ultrasonic bulk wave testing: A review10.1016/j.ultras.2018.03.003 ↗
21. Browne, B. (1997). Time of flight diffraction its limitations–actual & perceived. E-J. Non. Destr. Test., 2, Available online: https://www.ndt.net/?id=179.
22. Study on intelligent and visualization method of ultrasonic testing of composite materials based on deep learning10.1016/j.apacoust.2023.109363 ↗
23. Neural network classification of flaws detected by ultrasonic means
24. The use of neural networks in ultrasonic flaw detection10.1016/S0263-2241(98)00075-X ↗
25. Time frequency and wavelet transform applied to selected problems in ultrasonics NDE
26. Flexible decision support system for ultrasound evaluation of fiber–metal aminates implemented in a DSP
27. Investigation of deep neural network with drop out for ultrasonic flaw classification in weldments10.1007/s12206-018-0610-1 ↗
28. Convolutional neural network for ultrasonic weldment flaw classification in noisy conditions10.1016/j.ultras.2018.12.001 ↗
29. Ultrasonic signal classification and imaging system for composite materials via deep convolutional neural networks10.1016/j.neucom.2016.11.066 ↗
30. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
31. Deep learning10.1038/nature14539 ↗
32. Deep learning in neural networks: An overview10.1016/j.neunet.2014.09.003 ↗
33. Ultrasonic signal enhancement for coarse grain materials by machine learning analysis10.1016/j.ultras.2021.106550 ↗
34. Intelligent denoise laser ultrasonic imaging for inspection of selective laser melting components with rough surface
35. Rashid, T. (2016). Make Your Own Neural Network, CreateSpace Independent Publishing Platform.