Skip to main navigation menu Skip to main content Skip to site footer

Vol. 25 No. 43 (2016)

Papers

Fractographic classification in metallic materials by using 3D processing and computer vision techniques

https://doi.org/10.19053/01211129.v25.n43.2016.5301

Published 2016-09-01

  • Maria Ximena Bastidas-Rodríguez
    • ,
  • Flavio A. Prieto-Ortíz
    • ,
  • Édgar Espejo-Mora

Maria Ximena Bastidas-Rodríguez
Universidad Nacional de Colombia (Bogotá D.C., Colombia).

Flavio A. Prieto-Ortíz
Universidad Nacional de Colombia (Bogotá D.C., Colombia).

Édgar Espejo-Mora
Universidad Nacional de Colombia (Bogotá D.C., Colombia).

Abstract

Failure analysis aims at collecting information about how and why a failure is produced. The first step in this process is a visual inspection on the flaw surface that will reveal the features, marks, and texture, which characterize each type of fracture. This is generally carried out by personnel with no experience that usually lack the knowledge to do it. This paper proposes a classification method for three kinds of fractures in crystalline materials: brittle, fatigue, and ductile. The method uses 3D vision, and it is expected to support failure analysis. The features used in this work were: i) Haralick’s features and ii) the fractal dimension. These features were applied to 3D images obtained from a confocal laser scanning microscopy Zeiss LSM 700. For the classification, we evaluated two classifiers: Artificial Neural Networks and Support Vector Machine. The performance evaluation was made by extracting four marginal relations from the confusion matrix: accuracy, sensitivity, specificity, and precision, plus three evaluation methods: Receiver Operating Characteristic space, the Individual Classification Success Index, and the Jaccard’s coefficient. Despite the classification percentage obtained by an expert is better than the one obtained with the algorithm, the algorithm achieves a classification percentage near or exceeding the 60 % accuracy for the analyzed failure modes. The results presented here provide a good approach to address future research on texture analysis using 3D data.

Keywords

Artificial Neural Network, brittle fracture, ductile fracture, fracture due to fatigue, Support Vector Machine, 3D data

PDF HTML

References

  1. E. Espejo, “Fallas por fractura y fractografía,” Notas de clase curso Análisis de Falla. Universidad Nacional de Colombia, Bogotá, 2013.
  2. M. Ipohorski, Fractografía, Aplicaciones al Análisis de Fallas. Comisión Nacional de Energía Atómica, Buenos Aires, 1988.
  3. H. Lauschmann and I. Nedbal, Auto-Shape Analysis of Image Textures in Fractography, Czech Technical University, Faculty of Nuclear Sciences and Physical Engineering, República Checa: Trojanova, 2002.
  4. O. Mendoza, B. Vargas, and J. Mendoza, “Digital Processing of Fractographic Images for Welded Joints on Microalloy Steel API5L-X52 Aged,“ IEEE Latin America Transactions, vol. 11(1), pp. 172-176, Feb. 2013. DOI: https://doi.org/10.1109/TLA.2013.6502798
  5. H. Lauschmann, O. Rácek, M. Túma, and I. Nedbal, “Textural Fractography”, Image Anal Stereol, vol. 21(4), pp. S49-S59, Dec. 2002. DOI: http://dx.doi.org/10.5566/ias.v21.pS49-S59. DOI: https://doi.org/10.5566/ias.v21.pS49-S59
  6. R. Ya. Kosarevych, O. Z. Student, L. M Svirs'ka, B. P Rusyn, and H. M. Nykyforchyn, “Computer analysis of characteristic elements of fractographic images,” Materials Science, vol. 48(4), pp. 474-481, Jan. 2013. DOI: http://dx.doi.org/10.1007/s11003-013-9527-0. DOI: https://doi.org/10.1007/s11003-013-9527-0
  7. O. Kolednik, S. Scherer, P. Schwarzbock, and P. Werth, “Quantitative fractography by means of a new digital image analysis system,” in ECF13, Amsterdam, pp. 1-7, Nov. 2000.
  8. M.P. Pradhan, R. Pradhan, and M.K Ghose, “Shape reconstruction of fracture surface for HSLA materials using photometric-stereo images,” in International Symposium on Devices MEMS, Intelligent Systems and Communication (ISDMISC), 2011.
  9. M. Khokhlov, A. Fischer, and D. Rittel, “Multi-Scale Stereo-Photogrammetry System for Fractographic Analysis Using Scanning Electron Microscopy,” Experimental Mechanics, vol. 52(8), pp. 975-991, Oct. 2012. DOI: http://dx.doi.org/10.1007/s11340-011-9582-0. DOI: https://doi.org/10.1007/s11340-011-9582-0
  10. J. Komenda, B. Maroli, and L. Höglund, “Recognition of patterns on fracture surfaces by automatic image analysis,” Image Anual Stereol, vol. 21 (3), pp. 207-213. DOI: http://dx.doi.org/10.5566/ias.v21.p207-213. DOI: https://doi.org/10.5566/ias.v21.p207-213
  11. K. Komai, K. Minoshima, and S. Ishii, “Recognition of Different Fracture Surface Morphologies using Computer Image Processing Technique,” JSME international journal. Ser. A, Mechanics and material engineering, vol. 36(2), pp. 220-227, 1993. DOI: https://doi.org/10.1299/jsmea1993.36.2_220
  12. K. Slamecka and J. Pokluda, “3D Analysis of Fatigue Fracture Morphology Generated by Combined Bending Torsion,” in Advanced Fracture Mechanics for Life and Safety Assesments, Stockholm, 2003.
  13. S. Stach, J. Cybo, J. Cwajna, and S. Roskosz, “Multifractal description of fracture morphology. Full 3D analysis of a fracture surface,” Materials Science-Poland, vol. 23(2), pp. 577-584, 2005.
  14. C. Leising, Fractography Analysis Using 3D Profilometry. Nanovea, 2010.
  15. R. M. Haralick, K. Shanmugam, and I. Dinstein, “Textural features for image classification,” IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-3(6), pp. 610-621, Nov. 1973. DOI: https://doi.org/10.1109/TSMC.1973.4309314
  16. Texture Directional - A Multi-Trace Attribute that Returns Textural Information Based on a StatisticalTexture Classification. Available: http://www.opendtect.org/500/doc/od_userdoc/content/app_a/text_dir.htm.
  17. F. Tsai, C. Chang, J. Rau, T. Lin, and G. Liu, “3D Computation of Gray Level Co-occurrence in Hyperspectral Image Cubes,” Lecture Notes in Computer Science, vol. 4679, pp. 429-440, 2007. DOI: http://dx.doi.org/10.1007/978-3-540-74198-5_33. DOI: https://doi.org/10.1007/978-3-540-74198-5_33
  18. L. Kenneth, Textured Image Segmentation. University of Southern California, 1980.
  19. P. Bourke, Box Counting Fractal Dimension of Volumetric Data, 2014. Available: http://paulbourke.net/fractals/cubecount/.
  20. A. R. Backes and O. M. Bruno, “Plant Leaf Identification Using Multi-scale Fractal Dimension,” Lecture Notes in Computer Science, vol. 5716, pp. 143-150, 2009. DOI: http://dx.doi.org/10.1007/978-3-642-04146-4_17. DOI: https://doi.org/10.1007/978-3-642-04146-4_17
  21. Introduction to Support Vector Machines. Available: http://docs.opencv.org/2.4/doc/tutorials/ml/introduction_to_svm/introduction_to_svm.html.
  22. J. A. K. Suykens and J. Vandewalle, “Least Squares Support Vector Machine Classiffers,” Neural Process. Letters, vol. 9(3), pp. 293-300, Jun. 1999. DOI: http://dx.doi.org/10.1023/A:1018628609742. DOI: https://doi.org/10.1023/A:1018628609742
  23. C. Staelin, Parameter Selection for Support Vector Machines. HP Laboratories Israel, 2002.
  24. Redes Neuronales: de la teoría a la práctica, 2014. Available: https://www.mql5.com/es/articles/497.
  25. T. Fawcett, ”An Introduction to ROC Analysis,” Pattern Recognition Letters, vol. 27(8), pp. 861-874, Jun. 2006. DOI: http://dx.doi.org/10.1016/j.patrec.2005.10.010. DOI: https://doi.org/10.1016/j.patrec.2005.10.010
  26. V. Labatut and H. Cheril, Accuracy Measures for the Comparison of Classifiers” in The 5th International Conference on Information Technology, Jordanie, 2011.
  27. M. X. Bastidas-Rodríguez, F. A. Prieto-Ortiz, and E. Espejo, “Fractographic classification in metallic materials by using computer vision,” Engineering Failure Analysis, vol. 59, pp. 237-252, Jan. 2016. DOI: http://dx.doi.org/10.1016/j.engfailanal.2015.10.008. DOI: https://doi.org/10.1016/j.engfailanal.2015.10.008
  28. A. Ahmadvand and M. Reza, “Rotation invariant texture classification using extended wavelet channel combining and LL channel filter bank,” Knowledge-Based Systems, vol. 97, pp.75-88, Apr. 2016. DOI: http://dx.doi.org/10.1016/j.knosys.2016.01.015. DOI: https://doi.org/10.1016/j.knosys.2016.01.015
  29. K. Hanbay, N. Alpaslan, M. Fatih, and D. Hanbay, “Principal curvatures based rotation invariant algorithms for ef fi cient texture classification,” Neurocomputing, vol. 199 (C), pp. 77-89, Jul. 2016. DOI: http://dx.doi.org/ 10.1016/j.neucom.2016.03.032. DOI: https://doi.org/10.1016/j.neucom.2016.03.032
  30. E. Ben Othmen, M. Sayadi, and F. Fniaech, “3D Gray Level Co-occurrence Matrices for Volumetric Texture Classification,” in 3rd International Conference on Systems and Control, Algeria, Oct., 2013. DOI: http://dx.doi.org/10.1109/ICoSC.2013.6750953. DOI: https://doi.org/10.1109/ICoSC.2013.6750953

Downloads

Download data is not yet available.

Similar Articles

1 2 > >> 

You may also start an advanced similarity search for this article.