Russian Federation
Russian Federation
Purpose: The article is devoted to the research of the integration of innovative technologies into non-destructive testing (NDT) systems on the railway rolling stock. Traditional NDT methods, such as ultrasonic, magnetic particle and eddy current inspection, as well as their potential and limitations are considered in the light of modern requirements to safety and operational efficiency. The focus is on the application of smart glasses and machine vision technologies as supporting tools for improving diagnostics accuracy, faster defect detection and better experts’ interaction. Smart glasses are considered as a means of visualizing real-time data making diagnostics processes faster and reducing dependence on operators’ proficiency. Machine vision technologies, in turn, provide automatic defect detection, which significantly reduces human error factor and improves inspection accuracy. Methods: The research includes analyzing current publications, studying the best NDT application practices in the railway industry, and technological forecasting based on the current trends. Particular attention is paid to the integration of smart glasses as a tool for real-time data visualization and the use of machine vision designed to automate the diagnostics process. Remote experts’ interaction and cloud platform integration for data analysis have also been discussed. Results: The integrated smart glasses and machine vision for rolling stock diagnostics has proved to increase diagnostics accuracy, make NDT process faster, and reduce human error. The use of the above-stated technologies enables efficient data analysis and real-time remedial recommendations. Practical significance: Based on the analysis conducted, the prospects of the innovative technology introduction in the processes of non-destructive testing (NDT) have been outlined. The above-stated technologies will improve safety, increase the diagnostics accuracy and optimize the rolling stock maintenance. In the modern era of artificial intelligence, the use of machine vision systems can provide a more accurate data processing for rolling stock maintenance, which will lead to significant labour cost reduction.
Non-destructive testing, rolling stock, smart glasses, artificial intelligence, railway transport
1. Klyuev V. V. Nerazrushayuschiy kontrol' i diagnostika: Spravochnik / V. V. Klyuev. — 3-e izd. — M.: Mashinostroenie, 2005. — 656 s.
2. Se Ven'yan. Issledovaniya po optimizacii arhitektury oborudovaniya stancii obnaruzheniya TEDS dlya sistemy obnaruzheniya neispravnostey pri rabote elektropoezda / Ven'yan Se // Tehnologiya Zheng Tie. — 2018. — № 4. — S. 46.
3. ALEGER. Umnye ochki dlya dopolnennoy real'nosti. — URL: https://alegerglobal.com/ ru/dopolnennaya-real'nost'/umnye-ochki/ (data obrascheniya: 10.08.2024).
4. Bahova L. V. Osnovnye vidy i metody nerazrushayuschego kontrolya detaley i uzlov zheleznodorozhnogo podvizhnogo sostava / L. V. Bahova // Vestnik nauki i tvorchestva. — 2017. — № 6(18).
5. Tehnologicheskaya instrukciya po nerazrushayuschemu kontrolyu detaley i sostavnyh chastey kolesnyh par vagonov pri remonte. Magnitoporoshkovyy metod. TI NK V.21-2.2019.
6. Pravila nerazrushayuschego kontrolya detaley i sostavnyh chastey kolesnyh par vagonov pri remonte. Cpecial'nye trebovaniya PR NK V.2
7. GOST 34656—2020. Osi kolesnyh par zheleznodorozhnogo podvizhnogo sostava metody nerazrushayuschego kontrolya.
8. PR NK V.3. Pravila nerazrushayuschego kontrolya detaley telezhek gruzovyh pri remonte, special'nye trebovaniya.
9. Kozlov M. V. Issledovanie metrologicheskih harakteristik vihretokovogo metod nerazrushayuschego kontrolya vagonnogo parka / M. V. Kozlov, A. A. Petrov, T. V. Levchuk // Innovacii i investicii. — 2021. — № 6.
10. RealWear. — URL: https://www.realwear.com/ (data obrascheniya:15.12.2024).
11. GRSE. — URL: https://grse.ru/blog/tehnologii/buduschee-promyshlennosti-kak-umnye-ochk/ (data obrascheniya: 24.10.2024).
12. Chzhan He. Intellektual'naya ekspluataciya i tehnicheskoe obsluzhivanie gorodskogo zheleznodorozhnogo transporta. Obnaruzhenie / He Chzhan, Hunvey Yi, Ci Cao // Issledovanie gorodskogo zheleznodorozhnogo transporta. — 2020. — T. 23. — № 4. — S. 89–93.
13. Malygin L. L. Optoelektronnaya sistema identifikacii ob'ektov podvizhnogo sostava ARSCIS na stancii Cherepovec Severnoy zheleznoy dorogi / L. L. Malygin, V. V. Moshnikov, V. A. Carev // Sbornik dokladov nauchno-prakticheskoy konferencii «Innovacionnye proekty, novye tehnologii i izobreteniya». — 27–28 oktyabrya 2005 g., Eksperimental'noe kol'co VNIIZhT. — M.: VGUP VNIIZhT, 2005. — S. 122–130.
14. Caplin A. E. Sovershenstvovanie metodov kontrolya detaley mehanicheskoy chasti elektropodvizhnogo sostava primeneniem optiko-elektronnyh sredstv: avtoref. disc. ... kand.tehn. nauk: 05.22.07 / A. E. Caplin. — SPb.: Peterburgskiy gosudarstvennyy universitet putey soobscheniya, 2011. — 18 s.
