We construct an artificial neural network, with the help of which and the coefficients of continuous wavelet transformation, we can automatically detect signals from transverse cracks in rails in the defectograms recorded by a flaw-detector car. In the case where the mother wavelet function of the continuous wavelet transform and a configuration of the artificial neural network are successfully chosen, we can detect signals from defects in the initial stages of their initiation, i.e., within the period of time when the signals are comparable with noise.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
V. O. Nichoha, “Modeling of disturbances of the magnetic field of a rail around a transverse crack,” Fiz.-Khim. Mekh. Mater., 45, No. 3, 96–105 (2009); English translation: Mater. Sci., 45, No. 3, 431–440 (2009).
V. O. Nichoha, М. V. Sim’yanovs’kyi, I. S. Kuchma, H. R. Trokhym, “Specific features of the detection of defects in rails under the conditions of the Lviv railroad,” Vidb. Obrob. Inform., Issue 34 (110), 42–48 (2011).
Е. Danylenko, А. Orlovs’kyi, А. Taturevych, et al., Classification and Catalog of Defects and Damages of the Elements of Switches of Railroad Rails in Ukraine [in Ukrainian], Art-Press, Dnipropetrovs’k (2000).
M. Yu. Korolev, Magnetodynamic Method for the Monitoring of Rails. Methodology of the Numerical Analysis of Fields and Signals [in Russian], Author’s Abstract of the Candidate-Degree Thesis (Engineering), St.-Petersburg (2003).
M. Sifuzzaman, M. R. Islam, and M. Z. Ali, “Application of wavelet transform and its advantages compared to Fourier transform,” J. Phys. Sci., 13, 121–134 (2009).
V. O. Nichoha, L. V. Vashchyshyn, I. V. Storozh, and V. М. Ivanchuk, “Application of the windowed Fourier transform to the analysis of signals of magnetic diagnostics of railroad rails,” in: Proc. of the 16th Internat. Scientific-Engineering Conf. “Electromagnetic and Acoustic Methods of Nondestructive Testing of Materials and Products” (LEOTEST-2011) (February 21–26, 2011, Slavs’ke) [in Ukrainian], Karpenko Physicomechanical Institute, Ukrainian National Academy of Sciences, Lviv (2011), pp. 134–139.
L. V. Vashchyshyn and V. O. Nichoha, “Criteria of detection of a signal from the transverse crack in a rail with the help of continuous wavelet transform,” Vidb. Obrob. Inform., Issue 38 (114), 69–74 (2013).
L. Vashchyshyn, V. Nichoha, and I. Storozh, “Artificial neural networks as a method for the identification of defects in railroad rails,” Inform.-Keruyuchi Syst. Zalizn. Transp., No. 5, 34–37 (2012).
P. Nazarko, Ocena Stanu Konstrukcji – Detekcja Uszkodzen z Zastosowaniem Sztucznych Sieci Neuronowych, Rzeszow (2009).
V. O. Nichoha, L. V. Vashchyshyn, and I. V. Storozh, “Formation of the “mother” wavelet function and the analysis of defecftoscopic signals from transverse cracks in rails,” Inform.-Keruyuchi Syst. Zalizn. Transp., No. 3, 61–69 (2012).
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated from Fizyko-Khimichna Mekhanika Materialiv, Vol. 50, No. 3, pp. 142–146, May–June, 2014.
Rights and permissions
About this article
Cite this article
Vashchyshyn, L.V., Nichoha, V.О. Detection of a Transverse Crack in Railheads with the Help of Wavelet Transforms and Neural Networks. Mater Sci 50, 468–473 (2014). https://doi.org/10.1007/s11003-014-9744-1
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11003-014-9744-1