Modeling of microscope images for early detection of fatigue cracks in structural materials

  • Najah F. Ghalyan
  • Ibrahim F. Ghalyan
  • Asok RayEmail author


From the perspectives of health monitoring and life extension of structural materials, this paper addresses the problem of early detection of fatigue cracks in metallic materials (e.g., polycrystalline alloys). To this end, optical images have been collected from an ensemble of test specimens to construct computationally efficient models of crack evolution; these images are segmented into two major categories. The first category comprises images of (structurally) healthy specimens, while the second category contains images of specimens with cracks, including those in early stages of crack evolution. Based on this information, algorithms for early detection of crack formation are formulated in the setting of image classification, where the bag-of-words (BoW) technique has been used to develop models of the sensed images from a microscope, resulting in computationally efficient crack detection algorithms. To evaluate the performance of these crack detection algorithms, experiments have been conducted on a special-purpose fatigue testing apparatus, equipped with a computer-controlled and computer-instrumented confocal microscope system. The results of experimentation with multiple test specimens show excellent crack detection capabilities when the proposed BoW-based feature extraction is combined with quadratic support vector machine (QSVM) for pattern classification. Comparative evaluation with other classification tools establishes superiority of the proposed BoW/QSVM technique.


Bag-of-words Crack detection Image classification 


Funding information

The work reported in this paper has been supported in part by the U.S. Air Force Office of Scientific Research (AFOSR) under Grant Nos. FA9550-15-1-0400 and FA9550-18-1-0135 in the area of dynamic data-driven application systems (DDDAS). Any opinions, findings, and conclusions in this paper are those of the authors and do not necessarily reflect the views of the sponsoring agencies.


  1. 1.
    Aeran A, Siriwardane S, Mikkelsen O, Langen I (2017) A new nonlinear fatigue damage model based only on s-n curve parameters. Int J Fatigue 103:327–341Google Scholar
  2. 2.
    Anwar SA, Abdullah MZ (2014) Micro-crack detection of multicrystalline solar cells featuring an improved anisotropic diffusion filter and image segmentation technique. EURASIP J Image Video Process 2014(1):15. Google Scholar
  3. 3.
    Bay H, Ess A, Tuytelaars T, Van Gool L (2008) Speeded-up robust features (SURF). Comput Vis Image Underst 110(3):346–359. Google Scholar
  4. 4.
    Bay H, Tuytelaars T, Van Gool L (2006) Surf: Speeded up robust features. In: Leonardis A, Bischof H, Pinz A (eds) Computer vision – ECCV 2006. Springer, Berlin, pp 404–417Google Scholar
  5. 5.
    Bertoni A, Folgieri R, Valentini G (2005) Bio-molecular cancer prediction with random subspace ensembles of support vector machines. NeurocomputingGoogle Scholar
  6. 6.
    Bishop CM (2006) Pattern recognition and machine learning. Springer, New YorkzbMATHGoogle Scholar
  7. 7.
    Bjerken C, Melin S (2003) A tool to model short crack fatigue growth using a discrete dislocation formulation. Int J Fatigue 25(6):559–566zbMATHGoogle Scholar
  8. 8.
    Bovsunovskii A (2014) Asynchronous connection of a turbine generator to the mains as a factor of fatigue damage of steam turbine shafting. Strength Mater 46(6):810–819Google Scholar
  9. 9.
    Caplin J, Ray A, Joshi S (2001) Robust damage-mitigating control of aircraft for high performance and structural durability. IEEE Trans Aerosp Electron Syst 37(3):849–862Google Scholar
  10. 10.
    Cha YJ, Choi W, Büyüköztürk O (2017) Deep learning-based crack damage detection using convolutional neural networks. Comput-Aided Civ Infrastructu Eng 32 (5):361–378. Google Scholar
  11. 11.
    Cook D, Berthelot Y (2001) Detection of small surface-breaking fatigue cracks in steel using scattering of Rayleigh waves. NDT E Int 34(7):483–492Google Scholar
  12. 12.
    Cubero-Fernandez A, Rodriguez-Lozano FJ, Villatoro R, Olivares J, Palomares JM (2017) Efficient pavement crack detection and classification. EURASIP J Image Video Process 2017(1):39. Google Scholar
  13. 13.
    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), vol. 1, pp 886–893.
  14. 14.
    Duda R, Hart P, Stork D (2012) Pattern classification, 2nd edn. Wiley, USAzbMATHGoogle Scholar
  15. 15.
    Emanuel Aldea SLHM (2015) Robust crack detection for unmanned aerial vehicles inspection in an a-contrario decision framework. J Electron Imaging 24:24–24–16. Google Scholar
  16. 16.
    Fernández A, Gómez S (2008) Solving non-uniqueness in agglomerative hierarchical clustering using multidendrograms. J Classif 25(1):43–65. MathSciNetzbMATHGoogle Scholar
  17. 17.
    Gaur V, Doquet V, Persent E, Mareau C, Roguet E, Kittel J (2016) Surface versus internal fatigue crack initiation in steel: influence of mean stress. Int J Fatigue 82:437–448Google Scholar
  18. 18.
    Ghalyan IFJ, Chacko SM, Kapila V (2018) Simultaneous robustness against random initialization and optimal order selection in bag-of-words modeling. Pattern Recogn Lett 116:135–142. Google Scholar
  19. 19.
    Grondal S, Delebarre C, Assaad J, Dupuis J, Reithler L (2002) Fatigue crack monitoring of riveted aluminium strap joints by lamb wave analysis and acoustic emission measurement techniques. NDT E Int 35 (3):137–146Google Scholar
  20. 20.
    Gupta S, Ray A, Keller E (2007) Online fatigue damage monitoring by ultrasonic measurements: a symbolic dynamics approach. Int J Fatigue 29(6):1100–1114zbMATHGoogle Scholar
  21. 21.
    Hastie T, Tibshirani R, Friedman J (2016) The elements of statistical learning: data mining, inference, and prediction, 2nd edn. Springer, BerlinzbMATHGoogle Scholar
  22. 22.
    Ho T (1998) The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine IntelligenceGoogle Scholar
  23. 23.
    Ishihara S, McEvily A (2002) Analysis of short fatigue crack growth in cast aluminium alloys. Int J Fatigue 24(11):1169–1174Google Scholar
  24. 24.
    Jasim IF, Plapper PW (2013) T-S fuzzy contact state recognition for compliant motion robotic tasks using gravitational search-based clustering algorithm. In: 2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pp 1–8.
  25. 25.
    Jasim IF, Plapper PW (2014) Contact-state monitoring of force-guided robotic assembly tasks using expectation maximization-based gaussian mixtures models. Int J Adv Manuf Technol 73(5):623–633. Google Scholar
  26. 26.
    Kallappa P (2000) Ray: Fuzzy wide-range control of fossil power plants for life extension and robust performance. Automatica 36:69–82MathSciNetzbMATHGoogle Scholar
  27. 27.
    Kwofie S, Rahbar N (2012) A fatigue driving stress approach to damage and life prediction under variable amplitude loading. Int J Damage Mechan 22:393–404Google Scholar
  28. 28.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444Google Scholar
  29. 29.
    Lee DG, Jang KC, Kuk JM, Kim IS (2005) Comparison of the fatigue life of f.f. shaft material according to various environmental temperatures. Int J Adv Manuf Technol 26(7):896–908. Google Scholar
  30. 30.
    Liu C, Jiang D, Chen J (2014) Coupled torsional vibration and fatigue damage of turbine generator due to grid disturbance. J Eng Gas Turb Power 136(6):062,501–1–062,501–9Google Scholar
  31. 31.
    Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110. Google Scholar
  32. 32.
    Manning C, Raghavan P, Schütze H (2008) Introduction to information retrieval. Cambridge University Press, CambridgezbMATHGoogle Scholar
  33. 33.
    Meggiolaro M, Castro J (2004) Statistical evaluation of strain-life fatigue crack initiation prediction. Int J Fatigue 26(5):463– 476Google Scholar
  34. 34.
    Modarres C, Astorga N, Droguett EL, Meruane V (2018) Convolutional neural networks for automated damage recognition and damage type identification. Struct Control Health Monitor 25(10):e2230. Google Scholar
  35. 35.
    Mohan A, Papageorgiou C, Poggio T (2001) Example-based object detection in images by components. IEEE Trans Pattern Anal Mach Intell 23(4):349–361. Google Scholar
  36. 36.
    Mohan A, Poobal S (2018) Crack detection using image processing: A critical review and analysis. Alexandria Eng J 57(2):787 – 798. Google Scholar
  37. 37.
    Murphy K (2012) Machine learning: a probabilistic perspective, 1st edn. The MIT Press, CambridgezbMATHGoogle Scholar
  38. 38.
    Ni F, Zhang J, Chen Z (2019) Pixel-level crack delineation in images with convolutional feature fusion. Struct Control Health Monitor 26(1):e2286. Google Scholar
  39. 39.
    Qu Z, Lin LD, Guo Y, Wang N (2015) An improved algorithm for image crack detection based on percolation model. IEEJ Trans Electr Electron Eng 10(2):214–221. Google Scholar
  40. 40.
    Ray A (2004) Stochastic measure of fatigue crack damage for health monitoring of ductile alloy structures. Struct Health Monit 3(3):245–263Google Scholar
  41. 41.
    Ray A, Caplin J (2000) Life extending control of aircraft: Trade-off between flight performance and structural durability. Aeronaut J 104(1039):397–408Google Scholar
  42. 42.
    Saggar M, Bouraoui C, Nasr A (2018) Fatigue reliability prediction of defective materials based on a useful equivalent wöhler curve. Int J Adv Manuf Technol 97(1):1011–1021. Google Scholar
  43. 43.
    Saggar M, Sallem H, Bouraoui C (2018) Fatigue life prediction under variable loading based on a new damage model devoted for defective material. Int J Adv Manuf Technol 95(1):431–443. Google Scholar
  44. 44.
    Slima KB, Penazzi L, Mabru C, Ronde-Oustau F (2013) Fatigue analysis-based numerical design of stamping tools made of cast iron. Int J Adv Manuf Technol 67(5):1643–1650. Google Scholar
  45. 45.
    Suresh S (2004) Fatigue of Materials, 2nd edn. Cambridge University Press, CambridgeGoogle Scholar
  46. 46.
    Szeliski R (2011) Computer vision: algorithms and applications. Springer, LondonzbMATHGoogle Scholar
  47. 47.
    Theodoridis S, Koutroumbas K (2008) Pattern recognition, 4th edn. Academic Press, USAzbMATHGoogle Scholar
  48. 48.
    Wu B, Liu Z, Yuan Z, Sun G, Wu C (2017) Reducing overfitting in deep convolutional neural networks using redundancy regularizer. In: Lintas A, Rovetta S, Verschure PF, Villa AE (eds) Artificial neural networks and machine learning – ICANN 2017. Springer International Publishing, Cham, pp 49–55Google Scholar
  49. 49.
    Wu L, Hoi SCH, Yu N (2010) Semantics-preserving bag-of-words models and applications. IEEE Trans Image Process 19(7):1908–1920. MathSciNetzbMATHGoogle Scholar
  50. 50.
    Yokoyama S, Matsumoto T (2017) Development of an automatic detector of cracks in concrete using machine learning. Procedia Eng 171:1250–1255. The 3rd International Conference on Sustainable Civil Engineering Structures and Construction Materials - Sustainable Structures for Future GenerationsGoogle Scholar
  51. 51.
    Zhang Y, Jin R, Zhou ZH (2010) Understanding bag-of-words model: a statistical framework. Int J Mach Learn Cybern 1(1):43–52. Google Scholar
  52. 52.
    Zilberstein V, Walrath K, Grundy D, Schlicker D, Goldfine N, Abramovici E, Yentzer T (2003) MWM eddy-current arrays for crack initiation and growth monitoring. Int J Fatigue 25(9-11):1147–1155Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  • Najah F. Ghalyan
    • 1
  • Ibrahim F. Ghalyan
    • 2
  • Asok Ray
    • 3
    Email author
  1. 1.Department of Mechanical EngineeringThe Pennsylvania State UniversityUniversity ParkUSA
  2. 2.Department of Mechanical and Aerospace Engineering, Tandon School of EngineeringNew York UniversityBrooklynUSA
  3. 3.Department of Mechanical Engineering and Department of MathematicsThe Pennsylvania State UniversityUniversity ParkUSA

Personalised recommendations