Defect Detection of Industrial Radiography Images of Ammonia Pipes by a Sparse Coding Model
Source abstract
Abstract
Pipeline transportation systems for liquid anhydrous ammonia require periodic inspections for pipe defects. Defects such as crack-like flaws, including those due to stress corrosion and fatigue crack growth and fatigue of welded joints, can be tested by in situ radiography testing (RT). It is required that the detection technique should reveal the defect region without any significant distortion. Imaging noise such as that due to radiation scattering reduces contrast over the whole or part of the image, causing a reduction in image quality. Various image processing methods can be utilized to improve the outcome of RT of pipes. The sparse coding model is a powerful contrast improvement algorithm, but it tends to eliminate imaging details, passing them off as noise. We present a novel implementation of the sparse coding model based on a probabilistic interpretation to improve defect detection in ammonia pipelines radiography images. The performance of this procedure was evaluated in radiographic images of defect and corrosion regions for different pipe types. For ammonia pipes, the technique was found to offer a significant improvement in defect detection while preserving imaging details.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Ultrasonics and Acoustic Wave Propagation · Geophysical Methods and Applications · Non-Destructive Testing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (20)
Show source-provided references
1. Young, M.J., Pearson, A.B.: Ammonia leakage, dispersion and risk assessment. IOR the Service Engineers Section of the Institute of Refrigeration at www.ior.org.uk (2015)
2. Sivaprasad, S., Narang, S.K., Singh, R.: Failure of high pressure ammonia line in a fertilizer plant—a case study. Eng. Fail. Anal. 13, 867–875 (2006). https://doi.org/10.1016/j.engfailanal.2005.07.00310.1016/j.engfailanal.2005.07.003 ↗
3. Kajiwara, G.: Examination of the X-ray piping diagnostic system using EGS4 (examination of the film and iron rust). In: Proceedings of the Second International Workshop on EGS, Tsukuba, Japan, pp. 199–208 (2000)
4. Yamamoto, E., Shiga, K., Kayano, R., Okazaki, T., Watanabe, H., Kiso, T., Tahara, T., Minami, F.: Guidelines for repair welding of pressure equipment in refineries and chemical plants. J. Press. Vessel Technol. 135(3), 034501–034501-12 (2013). https://doi.org/10.1115/1.402372910.1115/1.4023729 ↗
5. Shafeek, H.I., Gadelmava, E.S., abdel-Shafy, A.A., Elewa, I.M.: Assessment of welding defects for gaspipeline radiographs using computer vision. NDT&E Int. 37, 291–299 (2004)10.1016/j.ndteint.2003.10.003 ↗
6. Alekseychuk, O., Zscherpel, U.: Probabilistic crack detection in digitized radiographs of weld inspection. In: Proceedings of the International Symposium on Computer Tomography and Image Processing for Industrial Radiology, Berlin, Germany pp. 211–222 (2003)
7. Yahaghi, E., Movafeghi, A., Mohmmadzadeh, N.: Enhanced radiographic imaging of defects in aircraft structure materials with the dehazing method. Nondestr. Test. Eval. 30(2), 138–146 (2015). https://doi.org/10.1080/10589759.2015.101825410.1080/10589759.2015.1018254 ↗
8. Kazantsev, I.G., Lemahieu, I., Salov, G.I., Denys, R.: Statistical detection of defects in radiographic images in nondestructive testing. Signal Process. 82, 791–801 (2002)10.1016/S0165-1684(02)00158-5 ↗
9. Zhang, L., Dong, W., Zhang, D., Shi, G.: Two-stage image denoising by principal component analysis with local pixel grouping. Pattern Recogn. 43(4), 1531–1549 (2010)10.1016/j.patcog.2009.09.023 ↗
10. Zhou, M., Chen, H., Paisley, J., Ren, L., Li, L., Xing, Zh, Dunson, D., Sapiro, G., Carin, L.: Nonparametric Bayesian dictionary learning for analysis of noisy and incomplete images. IEEE Trans. Image Process. 21(1), 130–144 (2012). https://doi.org/10.1109/TIP.2011.216007210.1109/TIP.2011.2160072 ↗
11. Efron, B., Hastie, T., Johnstone, I., Tibshirani, R.: Least angle regression. Ann. Stat. 32(2), 407–499 (2004)10.1214/009053604000000067 ↗
12. Yang, J., Yu, K., Gong, Y., Huang, T.: Linear spatial pyramid matching using sparsecoding for image classification. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR’09) (2009). https://doi.org/10.1109/CVPR.2009. 520675710.1109/CVPR.2009.%205206757 ↗
13. Lee, H., Battle, A., Raina, R., Ng, A.Y.: Efficient sparse coding algorithms. In: Neural Information Processing Systems (NIPS’06) (2006)10.7551/mitpress/7503.003.0105 ↗
14. Elad, M., Aharon, M.: Image denoising via learned dictionaries and sparse representation. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR’06) (2006)10.1109/CVPR.2006.142 ↗
15. Donoho, D.L., Elad, M.: Optimally sparse representation in general (non-orthogonal) dictionaries via $$\ell $$ ℓ 1 minimization. Proc. Natl. Acad. Sci. USA 100(5), 2197–2202 (2003)10.1073/pnas.0437847100 ↗
16. Daubechies, I., Defrise, M., De Mol, C.: An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun. Pure Appl. Math. 57, 1413–1457 (2004)10.1002/cpa.20042 ↗
17. Cai, J., Candes, E., Shen, Z.: A singular value thresholding algorithm 659 for matrix completion. SIAM J. Optim. 20(4), 1956–1982 (2010)
18. ISO 17636-2: Non-destructive testing of welds—radiographic testing—Part 2: X- and gamma-ray techniques with digital detectors (2013)
19. EN 16407-2: Non-destructive testing—radiographic inspection of corrosion and deposits in pipes by X- and gamma rays Part 2: double wall radiographic inspection (2014)
20. ISO19232-5: Non-destructive testing—image quality of radiographs—Part 5: determination of the image unsharpness value using duplex wire-type image quality indicators $$2^{{\rm nd}}$$ 2 nd edition (2013)