eesti teaduste
akadeemia kirjastus
SINCE 1952
Proceeding cover
of the estonian academy of sciences
ISSN 1736-7530 (Electronic)
ISSN 1736-6046 (Print)
Impact Factor (2021): 1.024
Quantification of cracks in beams on the Pasternak foundation using Haar wavelets and machine learning; pp. 16–29
PDF | 10.3176/proc.2022.1.02

Helle Hein, Ljubov Jaanuska

The inverse problem of crack identification, localisation and severity quantification is addressed in this article. The open cracks are simulated numerically in a homogeneous Euler–Bernoulli beam. The beam rests on the Pasternak foundation. Under the assumption that the size of the crack is small compared to the height of the beam, it is shown that the problem can be solved in terms of crack-induced changes in the natural frequencies or mode shapes. Predictions of the crack characteristics (location and severity) are made by artificial neural networks or random forests. The dimensionless natural frequency parameters or the first mode shape transformed into the Haar wavelet coefficients are used at the inputs of the machine learning methods. The numerical examples indicate that the combined approach of the natural frequencies, Haar wavelets, and machine learning produces accurate predictions. The results presented in the article can help in understanding the behaviour of more complex structures under similar conditions and provide apparent influence on the design of beams.


1. Addison, P. S. The Illustrated Wavelet Transform Handbook. Institute of Physics Publishing, Bristol and Philadelphia, 2002.

2. Ajayan, A. Higher mode natural frequencies of stepped beam using spectral finite elements. Master’s thesis. Rourkela National Institute of Technology, India, 2013.

3. Ansari, R., Gholami, R., Hosseini, K. and Sahmani, S. A sixth-order compact finite difference method for vibrational analysis of nanobeams embedded in an elastic medium based on nonlocal beam theory. Math. Comput. Model., 2011, 54(11), 2577–2586.

4. Aziz, I. and Amin, R. Numerical solution of a class of delay differential and delay partial differential equations via Haar wavelet.  Appl. Math. Model., 2016, 40(23–24), 10286–10299.

5. Aziz, I., Siraj-ul-Islam and Šarler, B. Wavelets collocation methods for the numerical solution of elliptic BV problems. Appl. Math. Model., 2013, 37(3), 676–694.

6. Cao, M., Ye, L., Zhou, L. M., Su, Z. and Bai, R. Sensitivity of fundamental mode shape and static deflection for damage identification in cantilever beams. Mech. Syst. Signal Process., 2011, 25(2), 630–643.

7. Celep, Z., Guler, K. and Demir, F. Response of a completely free beam on a tensionless Pasternak foundation subjected to dynamic load. Struct. Eng. Mech., 2011, 37(1), 61–77.

8. Chen, B., Lin, B., Zhao, X., Zhu, W., Yang, Y. and Li, Y. Closed-form solutions for forced vibrations of a cracked double-beam system interconnected by a viscoelastic layer resting on Winkler–Pasternak elastic foundation. Thin-Walled Struct., 2021, 163, 107688.

9. Dimarogonas, A. D., Paipetis, S. A. and Chondros, T. G. Analytical Methods in Rotor Dynamics. Springer Netherlands, 2013.

10. Elishakoff, I. Some unexpected results in vibration of non-homogeneous beams on elastic foundation. Chaos Solit. Fractals, 2001, 12(12), 2177–2218.

11. Feklistova, L. and Hein, H. Crack localization in Euler–Bernoulli beams. In Proceedings of the 2nd International Conference Optimization and Analysis of Structures, Tartu, Estonia, August 25–27, 2013 (Lellep, J. and Puman, E., eds). University of Tartu Press, 35–38.

12. Hadjileontiadis, L. J., Douka, E. and Trochidis, A. Fractal dimension analysis for crack identification in beam structures. Mech. Syst. Signal Process., 2005, 19(3), 659–674.

13. Hakim, S. J. S., Razak, H. A. and Ravanfar, S. A. Fault diagnosis on beam-like structures from modal parameters using artificial neural networks. Measurement, 2015, 76, 45–61.

14. Hakim, S. J. S., Razak, H. A., Ravanfar, S. A. and Mohammadhassani, M. Structural damage detection using soft computing method. In Structural Health Monitoring, Vol. 5 (Wicks, A., ed.). Springer, Cham, 2014, 143–151.

15. Hein, H. and Feklistova, L. Free vibrations of non-uniform and axially functionally graded beams using Haar wavelets. Eng. Struct., 2011, 33(12), 3696–3701.

16. Hein, H. and Jaanuska, L. Comparison of machine learning methods for crack localization. Acta et Comment. Univ. Tartu. de Math., 2019, 23(1), 125–142.

17. Hsiao, C.-H. and Wang, W.-J. State analysis of time-varying singular nonlinear systems via Haar wavelets. Math. Comput. Simul., 1999, 51(1–2), 91–100.

18. Jaanuska, L. and Hein, H. Crack identification in beams using Haar wavelets and machine learning methods. Int. J. Mech., 2016, 10, 281–287. 

19. Jayawardhana, M., Zhu, X., Liyanapathirana, R. and Gunawardana, U. Statistical damage sensitive feature for structural damage detection using AR model coefficients. Adv. Struct. Eng., 2015, 18(10), 1551–1562.

20. Karnovsky, I. A. and Lebed, O. I. Formulas for Structural Dynamics. McGraw-Hill, New York, NY, 2001.

21. Konar, P. and Chattopadhyay, P. Bearing fault detection of induction motor using wavelet and Support Vector Machines (SVMs). Appl. Soft Comput., 2011, 11(6), 4203–4211.

22. Lepik, Ü. Numerical solution of differential equations using Haar wavelets. Math. Comput. Simul., 2005, 68(2), 127–143.

23. Lepik, Ü. and Hein, H. Haar Wavelets: With Applications. Springer International Publishing Switzerland, 2014.

24. Li, J. and Hua, H. Spectral finite element analysis of elastically connected double-beam systems. Finite Elem. Anal. Des., 2007, 43(15), 1155–1168.

25. Mahmoud, M. A. and Kiefa, M. A. A. Neural network solution of the inverse vibration problem. NDT E Int., 1999, 32(2), 91–99.

26. Majak, J., Pohlak, M., Karjust, K., Eerme, M., Kurnitski, J. and Shvartsman, B. S. New higher order Haar wavelet method: application to FMG structures. Compos. Struct., 2018, 201, 72–78.

27. Majak, J., Shvartsman, B. S., Kirs, M., Pohlak, M. and Herranen, H. Convergence theorem for the Haar wavelet based discretization method. Compos. Struct., 2015, 126, 227–232.

28. Matbuly, M. S., Ragb, O. and Nassar, M. Natural frequencies of a functionally graded cracked beam using the differential quadrature method. Appl. Math. Comput., 2009, 215, 2307–2316.

29. Misiti, M., Misiti, Y., Oppenheim, G. and Poggi, J.-M. Wavelet Toolbox User’s Guide. The MathWorks, Natick, MA, 1997.

30. Misiti, M., Misiti, Y., Oppenheim, G. and Poggi, J.-M. (eds). Wavelets and their Applications. Wiley, 2013.

31. Ndambi, J.-M., Vantomme, J. and Harri, K. Damage assessment in reinforced concrete beams using eigenfrequencies and mode shape derivatives. Eng. Struct., 2002, 24(4), 501–515.

32. Ostachowicz, W. and Güemes, J. A. New Trends in Structural Health Monitoring. Springer, Vienna, 2013.

33. Özdemir, Y. I. Development of a higher order finite element on a Winkler foundation. Finite Elem. Anal. Des., 2012, 48, 1400–1408.

34. Pervaiz, N. and Aziz, I. Haar wavelet approximation for the solution of cubic nonlinear Schrodinger equations. Phys. A: Stat. Mech. Appl., 2020, 545, 123738.

35. Quek, S.-T., Wang, Q., Zhang, L. and Ang, K.-K. Sensitivity analysis of crack detection in beams by wavelet technique. Int. J. Mech. Sci., 2001, 43(12), 2899–2910.

36. Rizos, P. F., Aspragathos, N. and Dimarogonas, A. Identification of crack location and magnitude in a cantilever beam from the vibration modes. J. Sound Vib., 1990, 138(3), 381–388.

37. De Rosa, M. A. and Maurizi, M. J. Dynamic analysis of multistep piles on Pasternak soil subjected to axial tip forces. J. Sound Vib., 1999, 219(5), 771–783.

38. Rucka, M. and Wilde, K. Application of continuous wavelet transform in vibration based damage detection method for beams and plates. J. Sound Vib., 2006, 297(3–5), 536–550.

39. Rucka, M. and Wilde, K. Crack identification using wavelets on experimental static deflection profiles. Eng. Struct., 2006, 28(2), 279–288.

40. Shifrin, E. I. and Ruotolo, R. Natural frequencies of a beam with an arbitrary number of cracks. J. Sound Vib., 1999, 222(3), 409–423.

41. Silva, T., Maia, N., Roque, A. and Travassos, J. Identification of elastic support properties on a Bernoulli–Euler beam. In  Proceedings of the 27th International Modal Analysis Conference, Orlando, FL, USA, February 9–12, 2009. Society for Experimental Mechanics, 2009, 4, 1848–1860.

42. Skrinar, M. and Lutar, B. A three-node beam finite element for transversely cracked slender beams on Winklerʼs foundation. Comput. Mater. Sci., 2012, 64, 260–264.

43. Ubertini, F., Comanducci, G. and Cavalagli, N. Vibration-based structural health monitoring of a historic bell-tower using output-only measurements and multivariate statistical analysis. Struct. Health Monit., 2016, 15(4), 438–457.

44. Wang, Y. Damage assessment in asymmetric buildings using vibration techniques. PhD thesis. Queensland University of Technology, Australia, 2018.

45. Worden, K., Staszewski, W. J. and Hensman, J. J. Natural computing for mechanical systems research: A tutorial overview. Mech. Syst. Signal Process., 2011, 25(1), 4–111.

46. Wu, Z. S. and Adewuyi, A. P. Vibration-based structural health monitoring technique using statistical features for data stability assessment and damage localization. Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems, 2009, 729233.

47. Yan, Y. J., Cheng, L., Wu, Z. Y. and Yam, L. Development in vibration-based structural damage detection technique. Mech. Syst. Signal Process., 2007, 21, 2198–2211.

Back to Issue