Magnetic method of rail track joint gaps automated measurement

Introduction. Methods of automatic measurement of rail track joint gaps are not accurate enough or require costly equipment and sensors. This is why joint gaps are still monitored manually in many cases. The work is intended to experiment and examine a new method of automatic measurement of gaps in bolted rail joints using magnetic flaw detection (MFL).

Materials and methods. The paper uses actual track inspection results obtained by a flaw detection car on one of the railroads of Russian Railways. A specially developed programme used magnetic channel signals to highlight bolted rail joint locations and determine the magnitude of the joint gaps. The joint gaps were also measured manually using video images of bolted joints obtained by the on-board rail video recording system.

Results. The authors obtained expressions for calculating the joint gap value using magnetic sensor signals. Small gaps (up to 8 mm) are estimated by amplitude, medium and large gaps (above 9 mm) — by the spatial parameter of the signals from joint gaps. The authors compared the gap measurements from the two specified methods: visual and magnetic.

Discussion and conclusion. The research confirmed that automatic identification of bolted joints and determination of the value of joint gaps by magnetic rail flaw detection are sufficiently reliable for practical application. A comparative analysis of the values of the video inspection and the magnetic method showed high accuracy of joint gap measurement when using the latter. The magnetic method signals show high stability and repeatability.

1. Verigo M.F. New methods in the establishment of standards for the device and maintenance of a seamless trac. Moscow: Intext Publ.; 2000. 184 p. (In Russ).

2. Karpuschenko N.I., Ardyshev I.K. New problems of continuously welded rail track maintenance in high traffic areas. The Siberian Transport University Bulletin. 2023;(1):5-14. (In Russ.). https://doi.org/10.52170/1815-9265_2023_64_5.

3. Antipov A.G., Markov A. A., Maksimova E.A. Using a magnetic flux leakage method to estimate railway track bolted joint gaps. Defektoskopiya. 2023;(6):11-25. (In Russ.). https://doi.org/10.52170/1815-9265_2023_64_5.

4. Stoyanovich G.M., Pupatenko V.V. Temperature deformations in the balance rails zone of the continuously welded rails. Railway Track and Facilities. 2019;(6):34-37. (In Russ.). EDN: https://www.elibrary.ru/ncpqla.

5. Shilov M. N., Alekseev D. V., Tretyakov A.A. Tools and technologies of the automated system of video control of infrastructure facilities. Railway Track and Facilities. 2021;(9):11-12. (In Russ.). EDN: https://www.elibrary.ru/gmhxoc.

6. Xiong L., Jing G., Wang J., Liu X., Zhang Y. Detection of Rail Defects Using NDT Methods. Sensors. 2023;23(10):4627. https://doi.org/10.3390/s23104627.

7. Yilmazer M., Karakose M., Aydin I. Detection and Measurement of Railway Expansion Gap with Image Processing. In: Proceedings of 2021 International Conference on Data Analytics for Business and Industry. Conference Paper, 25–26 October 2021, Sakheer. Sakheer: IEEE; 2021. p. 515–519. https://doi.org/10.1109/ICDABI53623.2021.9655906.

8. Gibert X., Patel V. M., Chellappa R. Robust Fastener Detection for Autonomous Visual Railway Track Inspection. In: Proceedings of 2015 IEEE Winter Conference on Applications of Computer Vision. Conference Paper, 5–9 January 2015, Hawaii. Hawaii: IEEE; 2015. p. 694–701. https://doi.org/10.1109/WACV.2015.98.

9. James A., Jie W., Xulei Y., Ye C., Ngan N.B., Yuxin L., et al. TrackNet – A Deep Learning Based Fault Detection for Railway Track Inspection. In: Proceedings of 2018 International Conference on Intelligent Rail Transportation (ICIRT), 12–14 December 2018, Singapore. Singapore: IEEE; 2018. p. 1–5. https://doi.org/10.1109/ICIRT.2018.8641608.

10. Wang T., Yang F., Tsui K-L. Real-Time Detection of Railway Track Component via One-Stage Deep Learning Networks. Sensors. 2020;20(15):4325. https://doi.org/10.3390/s20154325.

11. Sukhobok Yu.A., Ten E.E., Ponomarchuk Yu.V., Shoberg K.A. Railway gap detection based on image processing and deep learning techniques. In: Actual theoretical, methodological and applied problems of virtual reality and artificial intelligence, 27–28 May 2021, Khabarovsk. Khabarovsk: Far Eastern State Transport University; 2021. p. 56–63 (In Russ). EDN: https://elibrary.ru/aekrdh.

12. Gurov E.A. Zabaykalskaya track video monitoring data decoding. Railway Track and Facilities. 2021;(8):36-37. (In Russ.). https://elibrary.ru/zivybk.

13. Tarabrin V.F., Yurchenko E.V., Lokhach A.V. EC ASUI SDMI — digital platform for predictive analysis and management of the state of railway infrastructure. Railway Track and Facilities. 2022;(6):25-28. (In Russ.). https://elibrary.ru/oiflcu.

14. Shur E.A. Best practices about rail defects: a review of the book “Defects of rails. Stresses and Damages”, Vol. 1 by K.-O. Edel, G. Budnitskiy, T. Schnitzer. Russian Railway Science Journal. 2021;80(3):182-185 (In Russ.). https://doi.org/10.21780/2223-9731-2021-80-3-182-185.

15. Gurvich A.K., Dovnar B.P., Kozlov V.B., Krug G.A., Kuzmina L.I., Matveev A.N. Non-destructive testing of rails during their operation and repair. Moscow: Transport Publ.; 1983. 318 p. (In Russ.).

16. Markov A.A., Politay P. G., Makhovikov S. P, Alekseev D. V., Kuznetsova E.A. The complex analysis of rail track condition with new AVIKON-03M flaw detector car. NDT World Review. 2013;(3):74-79. (In Russ.). https://elibrary.ru/rtemhp.

17. Antipov A.G., Markov A.A. 3D simulation and experiment on high speed rail MFL inspection. NDT & E International. 2018;(98):177-185. https://doi.org/10.1016/j.ndteint.2018.04.011.

18. Markov A.A., Antipov A.G., Karelin M.V. Reliability of automated recognition of mfl signals from rail track structure elements. Kontrol’. Diagnostika. 2018;(3):16-27. (In Russ.). https://doi.org/10.14489/td.2018.03.pp.016-027.

19. Markov A.A., Antipov A.G. Magnet rail flaw detection. New Opportunities. [S. l.]: LAP Lambert Academic Publishing; 2018. 112 p. (In Russ.).

20. Markov A.A., Antipov A. G., Karelin M.V., Maksimova E.A. Magnetic method to assess the condition of a jointless railway track. Railway Track and Facilities. 2024;(2):4-7. (In Russ.). EDN: https://elibrary.ru/abfsfr.