Abstract—
Nondestructive testing of rails is regularly conducted using various approaches and methods, including magnetic and eddy current testing methods, to ensure railroad safety. Automatic analysis of large data arrays (defectograms) from the corresponding equipment is an important problem. The analysis is the process of detecting defective pieces and identifying structural elements of a railroad track using defectograms. This article considers the problem of recognizing patterns of structural elements of railroad rails in defectograms of multichannel magnetic and eddy current defectoscopes. Three classes of structural elements of a railroad track are investigated: (1) a bolted joint with a straight or beveled rail connection, (2) a flash butt rail weld, and (3) an aluminothermic rail weld. Patterns that cannot be assigned to these three classes are conventionally considered as defects and are attributed to a separate fourth class. Patterns of structural elements are recognized in defectograms using a neural network based on the TensorFlow open library. For this purpose, each defectogram area selected for analysis is converted into a grayscale image with a size of 20 by 39 pixels.
Similar content being viewed by others
REFERENCES
Kuzmin, E.V., Gorbunov, O.E., Plotnikov, P.O., and Tyukin, V.A., On finding a threshold of useful signals in the analysis of magnetic and eddy current defectograms, Model. Anal. Inf. Sist., 2017, vol. 24, no. 6, pp. 760–771.
Kuzmin, E.V., Gorbunov, O.E., Plotnikov, P.O., and Tyukin, V.A., An efficient algorithm for finding a threshold of useful signals in the analysis of magnetic and eddy current defectograms, Model. Anal. Inf. Sist., 2018, vol. 25, no. 4, pp. 382–387.
Markov, A.A. and Kuznetsova, E.A., Defektoskopiya rel’sov. Formirovanie i analiz signalov (Rail Defectoscopy. Formation and Analysis of Signals), book 1: Osnovy (Basics), St. Petersburg: Kul’tInformPress, 2010.
Markov, A.A. and Kuznetsova, E.A., Defektoskopiya rel’sov. Formirovanie i analiz signalov (Rail Defectoscopy. Formation and Analysis of Signals), book 2: Rasshifrovka defektogramm (Defectogram Decoding), St. Petersburg: Ul’tra Print, 2014.
Tarabrin, V.F., Zverev, A.V., Gorbunov, O.E., and Kuzmin, E.V., About data filtration of the defectogram automatic interpretation by hardware and software complex “Astra,” V Mire Nerazrushayushchego Kontrolya, 2014, vol. 64, no. 2, pp. 5–9.
Simard, P.Y., Steinkraus, D., and Platt, J.C., Best practices for evolution neural networks applied to visual document analysis, 7th International Conference on Document Analysis and Recognition (ICDAR-2003) (August 3–6, 2003, Edinburgh, Scotland, UK), 2003, pp. 958–962.
Goodfellow, I., Bengio, Y., and Courville, A., Deep Learning, MIT Press, 2016.
Chollet, F., Deep Learning with Python, Manning Publications Co., 2018.
TensorFlow. https://www.tensorflow.org/.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
The authors declare that they have no conflicts of interest.
Additional information
Translated by O. Pismenov
About this article
Cite this article
Kuzmin, E.V., Gorbunov, O.E., Plotnikov, P.O. et al. Application of Neural Networks for Recognizing Rail Structural Elements in Magnetic and Eddy Current Defectograms. Aut. Control Comp. Sci. 53, 628–637 (2019). https://doi.org/10.3103/S0146411619070137
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411619070137