Materials Science

, Volume 54, Issue 3, pp 333–338 | Cite as

Prediction of the Diagrams of Fatigue Fracture of D16T Aluminum Alloy by the Methods of Machine Learning

  • О. P. YasniiEmail author
  • O. А. Pastukh
  • Yu. І. Pyndus
  • N. S. Lutsyk
  • I. S. Didych

By the methods of machine learning (neural networks, boosted trees, random forests, support-vector machines, and k -nearest neighbors), we plotted the diagrams of fatigue fracture of D16T aluminum alloy under regular loading with a stress ratio R = 0, 0.2, 0.4, and 0.6. The obtained results are in good agreement with the experimental data. It was discovered that the method of neural networks gives the least prediction error equal to 3.2 and 2.5% in tested samples.


fatigue crack growth stress intensity factor load ratio durability neural network machine learning 


  1. 1.
    I. V. Varfolomeev and O. P. Yasnii, “Modeling of fracture of cracked structural elements with the use of probabilistic methods,” Fiz.-Khim. Mekh. Mater., 44, No. 1, 76–83 (2008); English translation: Mater. Sci., 44, No. 1, 87–96 (2008).Google Scholar
  2. 2.
    O. P. Yasnii, A. R. Sobchak, and V. P. Yasnii, “Estimation of the probability of fracture of the superheater collector of a thermal power plant,” Fiz.-Khim. Mekh. Mater., 50, No. 3, 63–68 (2014); English translation: Mater. Sci., 50, No. 3, 381–387 (2014).Google Scholar
  3. 3.
    T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer, New York (2009).CrossRefGoogle Scholar
  4. 4.
    J. R. Mohanty, B. B. Verma, D. R. K. Parhi, and D. R. Ray, “Application of artificial neural network for predicting fatigue crack propagation life of aluminum alloys,” Arch. Comput. Mat. Sci. Surf. Eng., 1, No. 3, 133–138 (2009).Google Scholar
  5. 5.
    R. M. V. Pidaparti and M. Palakal, “Neural network approach to fatigue-crack-growth predictions under aircraft spectrum loadings,” J. Aircraft, No. 4, 825−831 (1995).Google Scholar
  6. 6.
    P. C. Paris and F. A. Erdogan, “Critical analysis of crack propagation laws,” J. Basic Eng., 85, No. 4, 528−534 (1963).CrossRefGoogle Scholar
  7. 7.
    V. T. Troshchenko, V. V. Pokrovskii, and A. V. Prokopenko, Crack Resistance of Metals under Cyclic Loads [in Russian], Naukova Dumka, Kiev (1987).Google Scholar
  8. 8.
    O. P. Yasnii and Yu. I. Pyndus, “Modeling of crack growth in D16ChT alloy for variable loading amplitudes,” Visn. Ternopil’ Derzh. Tekh. Univ., 12, No. 1, 25−32 (2007).Google Scholar
  9. 9.
    W. Elber, “Fatigue crack closure under cyclic tension,” Eng. Fract. Mech., 2, No. 1, 37−45 (1970).CrossRefGoogle Scholar
  10. 10.
    W. Elber, “The significance of fatigue crack closure,” Damage Tolerance Aircraft Struct., 486, 230–242 (1971).CrossRefGoogle Scholar
  11. 11.
    M. Klesnil and P. Lukas, “Effect of stress ratio on fatigue crack growth,” Mat. Sci. Eng., 9, 231−240 (1972).CrossRefGoogle Scholar
  12. 12.
    D. Kujawski and F. Ellyin, “A fatigue crack growth model with load ratio effects,” Eng. Fract. Mech., 28, 367−378 (1987).CrossRefGoogle Scholar
  13. 13.
    S. Dinda S. and D. Kujawski, “Correlation and prediction of fatigue crack growth for different R-ratios using K max and ΔK + parameters,” Eng. Fract. Mech., 71, 1779−1790 (2004).Google Scholar
  14. 14.
    D. Kujawski, “A new (ΔK + K max )0.5 driving force parameter for crack growth in aluminum alloys,” Int. J. Fatigue, 23, 733−740 (2001).Google Scholar
  15. 15.
    F. Gorunescu, Data Mining: Concepts, Models, and Techniques, Springer, Heidelberg (2011).Google Scholar
  16. 16.
    P. D. Wasserman, Neural Computing: Theory and Practice, Coriolis Group (Sd), New York (1989).Google Scholar
  17. 17.
    P. Yasnii, Yu. Pyndus, and V. Fostyk, “Influence of loading ratio on the characteristics of cyclic crack resistance of D16T aluminum alloy,” Visn. Ternopil’ Derzh. Tekh. Univ., 12, No. 1, 7–12 (2007).Google Scholar
  18. 18.
    C. A. R. P. Baptista, A. M. L. Adib, M. A. S. Torres, and V. A. Pastoukhov, “Describing fatigue crack growth and load ratio effects in Al 2524 T3 alloy with an enhanced exponential model,” Mech. Mat., 51, 66–73 (2012).CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • О. P. Yasnii
    • 1
    Email author
  • O. А. Pastukh
    • 1
  • Yu. І. Pyndus
    • 1
  • N. S. Lutsyk
    • 1
  • I. S. Didych
    • 1
  1. 1.Pulyui Ternopil’ National Technical UniversityTernopil’Ukraine

Personalised recommendations