Deploying Machine Learning for Radiography of Aerospace Welds
Source abstract
Abstract
Abstract Artificial intelligence is providing new possibilities for analysis in the field of industrial radiography. As capabilities evolve, there is the need for knowledge concerning how to deploy these technologies in practice and benefit from the new automatically generated information. In this study, automatic defect recognition based on machine learning was deployed as an aid in industrial radiography of laser welds in an aerospace component, and utilized to produce statistics for improved quality control. A multi-model approach with an added weld segmentation step improved the inference speed and decreased false calls to improve field use. A user interface with visualization options was developed to display the evaluation results. A dataset of 451 radiographs was automatically analysed, yielding 10037 indications with size and location information, providing capability for statistical analysis beyond what is practical to carry out with manual annotation. The distribution of indications was modeled as a product of the probability of detection and an exponentially decreasing underlying flaw distribution, opening the possibility for model reliability assessment and predictive capabilities on weld defects. An analysis of the indications demonstrated the capability to automatically detect both large-scale trends and individual components and welds that were more at risk of failing the inspection. This serves as a step towards smarter utilization of non-destructive evaluation data in manufacturing.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Welding Techniques and Residual Stresses · Non-Destructive Testing Techniques · Advanced X-ray and CT Imaging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (54)
Show source-provided references
1. Vrana, J., Meyendorf, N., Ida, N., et al.: Introduction to NDE 4.0. Handbook Nondest. Eval. 40, 1–28 (2021). https://doi.org/10.1007/978-3-030-48200-8_43-210.1007/978-3-030-48200-8_43-2 ↗
2. Bond, L.J.: From nondestructive testing to prognostics: Revisited. Handbook Nondestr. Eval. 40, 1–28 (2021). https://doi.org/10.1007/978-3-030-48200-8_34-110.1007/978-3-030-48200-8_34-1 ↗
3. Bertovic, M., Virkkunen, I.: NDE 4.0: new paradigm for the NDE inspection personnel. In: Handbook of Nondestructive Evaluation 40, 1–31 (2021). https://doi.org/10.1007/978-3-030-48200-8_9-110.1007/978-3-030-48200-8_9-1 ↗
4. Aldrin, J.C.: The human-machine interface (HMI) with NDE 4.0 systems. In: Handbook of Nondestructive Evaluation 4.0. Springer, p. 477–497, https://doi.org/10.1007/978-3-030-73206-6_32(2022)10.1007/978-3-030-73206-6_32 ↗
5. International Organization for Standardization (2007) Welding and allied processes - classification of geometric imperfections in metallic materials - part 1: Fusion welding (ISO 6520-1:2007)
6. International Organization for Standardization (2014) Welding - fusion-welded joints in steel, nickel, titanium and their alloys (beam welding excluded) - quality levels for imperfections (ISO 5817:2014)
7. Han, X., Yang, Z., Ma, Y., et al.: Porosity distribution and mechanical response of laser-mig hybrid butt welded 6082–t6 aluminum alloy joint. Opt. Laser Technol. 132(106), 511 (2020). https://doi.org/10.1016/j.optlastec.2020.10651110.1016/j.optlastec.2020.106511 ↗
8. Elmer, J., Vaja, J., Pong, R., et al.: The effect of Ar and N2 shielding gas on laser weld porosity in steel, stainless steel, and nickel. Welding J. 2015(LLNL-JRNL-663819) (2015)
9. Nacereddine, N., Zelmat, M., Belaifa, S.S., et al.: Weld defect detection in industrial radiography based digital image processing. Trans. Eng. Comput. Technol. 2, 145–148 (2005). https://doi.org/10.5281/zenodo.133064110.5281/zenodo.1330641 ↗
10. Mery, D., Arteta, C.: Automatic defect recognition in X-ray testing using computer vision. In: 2017 IEEE winter conference on applications of computer vision (WACV), IEEE, pp 1026–1035, (2017) https://doi.org/10.1109/WACV.2017.11910.1109/WACV.2017.119 ↗
11. Mery, D.: Aluminum casting inspection using deep object detection methods and simulated ellipsoidal defects. Mach. Vision Appl. 32(3), 1–16 (2021). https://doi.org/10.1007/s00138-021-01195-510.1007/s00138-021-01195-5 ↗
12. Du, W., Shen, H., Fu, J., et al.: Approaches for improvement of the X-ray image defect detection of automobile casting aluminum parts based on deep learning. NDT & E Int. 107(102), 144 (2019). https://doi.org/10.1016/j.ndteint.2019.10214410.1016/j.ndteint.2019.102144 ↗
13. Jiang, H., Hu, Q., Zhi, Z., et al.: Convolution neural network model with improved pooling strategy and feature selection for weld defect recognition. Weld. World 65(4), 731–744 (2021). https://doi.org/10.1007/s40194-020-01027-610.1007/s40194-020-01027-6 ↗
14. Tyystjärvi, T., Virkkunen, I., Fridolf, P., et al.: Automated defect detection in digital radiography of aerospace welds using deep learning. Weld. World 66(4), 643–671 (2022). https://doi.org/10.1007/s40194-022-01257-w10.1007/s40194-022-01257-w ↗
15. Baniukiewicz, P.: Automatic segmentation of radiographic images in industrial applications. Arch. Elect. Eng. (2011). https://doi.org/10.2478/mms-2014-004610.2478/mms-2014-0046 ↗
16. Yu, H., Li, X., Song, K., et al.: Adaptive depth and receptive field selection network for defect semantic segmentation on castings X-rays. NDT & E Int. 116(102), 345 (2020). https://doi.org/10.1016/j.ndteint.2020.10234510.1016/j.ndteint.2020.102345 ↗
17. Yang, L., Wang, H., Huo, B., et al.: An automatic welding defect location algorithm based on deep learning. NDT & E Int. 120(102), 435 (2021). https://doi.org/10.1016/j.ndteint.2021.10243510.1016/j.ndteint.2021.102435 ↗
18. Golodov, V., Maltseva, A.: Approach to weld segmentation and defect classification in radiographic images of pipe welds. NDT & E Int. 127(102), 597 (2022). https://doi.org/10.1016/j.ndteint.2021.10259710.1016/j.ndteint.2021.102597 ↗
19. Tokime, R., Maldague, X., Perron, L.: Automatic defect detection for X-ray inspection: Identifying defects with deep convolutional network. Proceedings of the Canadian Institute for Non-destructive Evaluation (CINDE), Edmonton, AB, Canada pp 18–20 (2019)
20. Ajmi, C., Zapata, J., Elferchichi, S., et al.: Deep learning technology for weld defects classification based on transfer learning and activation features. Adv. Mater. Sci. Eng. (2020). https://doi.org/10.1155/2020/157435010.1155/2020/1574350 ↗
21. Liu, W., Shan, S., Chen, H., et al.: X-ray weld defect detection based on AF-RCNN. Weld. World (2022). https://doi.org/10.1007/s40194-022-01281-w10.1007/s40194-022-01281-w ↗
22. Gamdha, D., Unnikrishnakurup, S., Rose, K., et al.: Automated defect recognition on X-ray radiographs of solid propellant using deep learning based on convolutional neural networks. J. Nondestr. Eval. 40(1), 1–13 (2021). https://doi.org/10.1007/s10921-021-00750-410.1007/s10921-021-00750-4 ↗
23. Jain, D.K., et al.: An evaluation of deep learning based object detection strategies for threat object detection in baggage security imagery. Pattern Recognit. Lett. 120, 112–119 (2019). https://doi.org/10.1016/j.patrec.2019.01.01410.1016/j.patrec.2019.01.014 ↗
24. Zhong, J., Zhang, F., Lu, Z., et al.: High-speed display-delayed planar X-ray inspection system for the fast detection of small fishbones. J. Food Process Eng. 42(3), e13,010 (2019). https://doi.org/10.1111/jfpe.1301010.1111/jfpe.13010 ↗
25. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)10.1038/nature14539 ↗
26. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1097–1105 (2012). https://doi.org/10.1145/306538610.1145/3065386 ↗
27. Rawat, W., Wang, Z.: Deep convolutional neural networks for image classification: a comprehensive review. Neural Comput. 29(9), 2352–2449 (2017). https://doi.org/10.1162/neco_a_0099010.1162/neco_a_00990 ↗
28. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv preprint arXiv:1409.1556
29. Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: International conference on machine learning, PMLR, pp 6105–6114, (2019) https://doi.org/10.48550/arXiv.1905.1194610.48550/arXiv.1905.11946 ↗
30. Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. (2015). https://doi.org/10.1109/TPAMI.2016.257703110.1109/TPAMI.2016.2577031 ↗
31. Redmon, J., Farhadi, A.: Yolov3: An incremental improvement (2018) . arXiv preprint arXiv:1804.02767
32. Lin, T.Y., Dollár, P., Girshick, R., et al.: Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117–2125 (2017), https://doi.ieeecomputersociety.org/10.1109/CVPR.2017.10610.1109/CVPR.2017.106 ↗
33. Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention, Springer, pp 234–241, (2015) https://doi.org/10.1007/978-3-319-24574-4_2810.1007/978-3-319-24574-4_28 ↗
34. He, K., Gkioxari, G., Dollár, P., et al.: Mask R-CNN. In: Proceedings of the IEEE international conference on computer vision, p. 2961–2969 (2017), https://doi.org/10.1109/ICCV.2017.32210.1109/ICCV.2017.322 ↗
35. Weiss, K., Khoshgoftaar, T.M., Wang, D.: A survey of transfer learning. J. Big data 3(1), 1–40 (2016). https://doi.org/10.1186/s40537-016-0043-610.1186/s40537-016-0043-6 ↗
36. Mery, D., Riffo, V., Zscherpel, U., et al.: Gdxray: The database of X-ray images for nondestructive testing. J. Nondestr. Eval. 34(4), 1–12 (2015). https://doi.org/10.1007/s10921-015-0315-710.1007/s10921-015-0315-7 ↗
37. International Organization for Standardization (2016) Non-destructive testing of welds - acceptance levels for radiographic testing - part 1: Steel, nickel, titanium and their alloys (ISO 10675-1:2016)
38. Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big data 6(1), 1–48 (2019). https://doi.org/10.1186/s40537-019-0197-010.1186/s40537-019-0197-0 ↗
39. Ganaie, M.A., Hu, M., et al.: Ensemble deep learning: a review (2021). arXiv preprint arXiv:2104.02395
40. Mullapudi, R.T., Mark, W.R., Shazeer, N., et al.: Hydranets: Specialized dynamic architectures for efficient inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 8080–8089, (2018) https://doi.org/10.1109/CVPR.2018.0084310.1109/CVPR.2018.00843 ↗
41. Xu, D., Shi, Y., Tsang, I.W., et al.: Survey on multi-output learning. IEEE Trans. Neural Netw. Learn. Syst. 31(7), 2409–2429 (2019)
42. Hashem, I.A.T., Yaqoob, I., Anuar, N.B., et al.: The rise of big data on cloud computing: Review and open research issues. Inf. Syst. 47, 98–115 (2015). https://doi.org/10.1016/j.is.2014.07.00610.1016/j.is.2014.07.006 ↗
43. Trinks, S., Felden, C.: Edge computing architecture to support real time analytic applications: A state-of-the-art within the application area of smart factory and industry 4.0. In: 2018 IEEE International Conference on Big Data (Big Data), IEEE, pp 2930–2939, (2018) https://doi.org/10.1109/BigData.2018.862264910.1109/BigData.2018.8622649 ↗
44. Garcia Lopez, P., Montresor, A., Epema, D., et al.: Edge-centric computing: vision and challenges. ACM SIGCOMM Comput. Commun. (2015). https://doi.org/10.1145/2831347.283135410.1145/2831347.2831354 ↗
45. Rausch, T., Hummer, W., Muthusamy, V., et al.: Towards a serverless platform for edge AI. In: 2nd USENIX Workshop on Hot Topics in Edge Computing (HotEdge 19) (2019)
46. NVIDIA (2022b) Meet Jetson, the Platform for AI at the Edge. Available: https://developer.nvidia.com/embedded-computing
47. Google (2023) Edge TPU. Available: https://cloud.google.com/edge-tpu
48. Al-Ali, F., Gamage, T.D., Nanayakkara, H.W., et al.: Novel casestudy and benchmarking of alexnet for edge ai: From cpu and gpu to fpga. In: 2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), IEEE, pp 1–4 (2020)10.1109/CCECE47787.2020.9255739 ↗
49. European Society of Radiology (ESR), Becker, C., Kotter, E., Fournier, L., Martí-Bonmatí, L.: Current practical experience with artificial intelligence in clinical radiology: a survey of the european society of radiology. Insights Imaging 13(1), 107 (2022). https://doi.org/10.1186/s13244-022-01247-y10.1186/s13244-022-01247-y ↗
50. Canoni-Meynet, L., Verdot, P., Danner, A., et al.: Added value of an artificial intelligence solution for fracture detection in the radiologist’s daily trauma emergencies workflow. Diagn. Interv. Imaging (2022). https://doi.org/10.1016/j.diii.2022.06.00410.1016/j.diii.2022.06.004 ↗
51. Bertovic, M.: A human factors perspective on the use of automated aids in the evaluation of NDT data. In: AIP conference proceedings, AIP Publishing LLC, p 020003, https://doi.org/10.1063/1.4940449(2016)10.1063/1.4940449 ↗
52. Deng, J., Dong, W., Socher, R., et al.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, Ieee, pp 248–255, https://doi.org/10.1109/CVPR.2009.5206848(2009)10.1109/CVPR.2009.5206848 ↗
53. NVIDIA (2022a) Jetson AGX Xavier Series. Available: https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-agx-xavier
54. Annis, C.: Mil-hdbk-1823a, nondestructive evaluation system reliability assessment (2009)