China’s railways now operate at higher speeds and heavier loads than before. Rails bear repeated wheel-rail impacts and friction over decades of service. This harsh environment leads to surface cracks, spalling, and wear – defects that threaten safety if left unchecked. Manual patrols are slow and subjective. Ultrasonic testing, while good for internal flaws, misses fine surface cracks. We present a two-dimensional (2D) optical imaging system for detecting rail surface cracks. The hardware includes an A3600CG18 industrial camera (Huarui Technology), a Vision Intelligence fixed-focus lens, and a high-density light emitting diode (LED) ring light. These components capture clear, low-noise images of the rail surface. The software pipeline handles image acquisition, preprocessing, feature extraction, and deep learning-based classification. Experiments show that the system suppresses glare, locates cracks accurately, and runs in real time. It offers a practical solution for automated railway track inspection.
References
[1] Wang, Y., Miao, B., Zhang, Y., Huang, Z., Xu, S. (2025) Review on rail damage detection technologies for high-speed trains. Applied Sciences, 15(14), 7725.
[2] Bai, T., Gao, J., Yang, J., Yao, D. (2021) A study on railway surface defects detection based on machine vision. Entropy, 23(11), 1437.
[3] Yin, M., Li, K., Cheng, X. (2020) A review on artificial intelligence in high-speed rail. Transportation Safety and Environment, 2(4), 247-259.
[4] Olivier, B., Guo, F., Qian, Y., Connolly, D. P. (2025) A review of computer vision for railways. IEEE Transactions on Intelligent Transportation Systems, 26(7), 11034-11065.
[5] Matei, A. T., Visan, A. I., Negut, I. (2025) Laser-fabricated micro/nanostructures: mechanisms, fabrication techniques, and applications. Micromachines, 16(5), 573.
[6] Sung, D., Hong, S., Lee, J. (2023) Numerical analysis of the rail surface crack propagation under rail uplift force: a parametric study on initial crack geometry. Engineering Failure Analysis, 153, 107542.
[7] Liu, H., Lv, H., Han, C., Zhao, Y. (2023) Vibration detection and degraded image restoration of space camera based on correlation imaging of rolling-shutter cmos. Sensors, 23(13), 5953.
[8] Rodríguez-Hernández, M., Crespo-Márquez, A., Sánchez-Herguedas, A., González-Prida, V. (2025) Digitalization as an enabler in railway maintenance: a review from “the international union of railways asset management framework” perspective. Infrastructures, 10(4), 96.
[9] Wang, Y., Miao, B., Zhang, Y., Huang, Z. (2026) Research on geometric parameter quantification of rail rolling contact fatigue crack damage based on 2D optical image. Scientific Reports, 16(1), 5715.
[10] Yaodong, W., Hang, Y., Baoqing, G., Hongmei, S., Zujun, Y. (2024) Research on real-time detection system of rail surface defects based on deep learning. IEEE Sensors Journal, 24(13), 21157-21167.
[11] Daniyan, I., Mpofu, K., Nwankwo, S. (2023) Design of a robot for inspection and diagnostic operations of rail track facilities. International Journal of Quality & Reliability Management, 40(3), 653-673.
[12] Mordia, R., Verma, A. K. (2025) Nondestructive testing methods for rail defects detection. High-Speed Railway, 3(2), 163-173.
[13] Kumar, A., Harsha, S. P. (2025) A systematic literature review of defect detection in railways using machine vision-based inspection methods. International Journal of Transportation Science and Technology, 18, 207-226.
Share and Cite
Ling, H., Wang, Y. (2026) Design of a Rail Surface Crack Damage Identification System Based on 2D Optical Images. Scientific Research Bulletin, 3(2), 108-113. https://doi.org/10.71052/srb2024/CGRD8508