Author(s)

YuYang Xia, ZhongFu Liu^*

Affiliation(s)

School of Information and Communication Engineering, Dalian Minzu University, Dalian 116600, Liaoning, China.

Corresponding Author

ZhongFu Liu

ABSTRACT

This research addresses the specific and crucial application scenario of railway track damage detection by designing and implementing a comprehensive intelligent detection system solution. At the hardware architecture level, the system meticulously selects the high-performance STM32F103 microcontroller as the core control unit. This unit offers fast processing speed, low power consumption, and high reliability, laying a solid foundation for the system's stable operation. Centered around this core control unit, the system integrates various functional modules, including high-precision detection modules like planar capacitive sensors for real-time and accurate collection of track status data. Simultaneously, the OpenMV visual processing module is utilized to achieve precise machine vision recognition of track surface defects, significantly enhancing the intuitiveness and accuracy of detection. Additionally, the system is equipped with a motor drive module to enable precise movement of the detection device. The system not only features excellent hardware configuration but also possesses powerful data processing capabilities, enabling real-time and efficient analysis and processing of the collected massive data, thereby significantly improving detection accuracy and timeliness. In terms of material selection, the system innovatively adopts new energy-saving and environmentally friendly materials, which not only substantially reduce the overall energy consumption of the system but also effectively extend the equipment's service life, markedly enhancing its durability. This system integrates numerous advantages such as efficient detection, energy saving, environmental protection, and low-cost operation, demonstrating broad application prospects and significant market promotion potential in the field of railway operation and maintenance. It is expected to provide a solid and powerful guarantee for the safe and stable operation of railways.

KEYWORDS

Microcontroller; Sensor; Rail damage; Planar capacitance; High efficiency and energy saving; OpenMV visual processing

CITE THIS PAPER

YuYang Xia, ZhongFu Liu. Rail damage detection system based on fusion of planar capacitive sensing and vision. Eurasia Journal of Science and Technology. 2025, 7(6): 5-12. DOI: https://doi.org/10.61784/ejst311.

REFERENCES

[1] Zhang M X, Wang K W, Yang Y L, et al. Enhanced Blind Separation of Rail Defect Signals with Time–Frequency Separation Neural Network and Smoothed Pseudo Wigner–Ville Distribution. Applied Sciences, 2025, 15 (7): 3546. DOI: 10.3390/APP15073546.

[2] Mao X G, Xia C L, Liu J Z, et al. A novel similarity measure based on dispersion-transition matrix and Jensen–Fisher divergence and its application on the detection of rail short-wave defects. Chaos, Solitons and Fractals: the interdisciplinary journal of Nonlinear Science, and Nonequilibrium and Complex Phenomena, 2025, 192, 115988. DOI: 10.1016/J.CHAOS.2025.115988.

[3] Gong W D, Akbar M F, Jawad G N, et al. The Optimization Method of Magnetic Flux Leakage Detection Equipment in Rail Surface Inspection Based on Finite Element Simulation. Integrated Ferroelectrics, 2024, 240 (8-9): 1205-1219. DOI: 10.1080/10584587.2024.2328859.

[4] Ding Y, Zhao Q, Li T, et al. A rail defect detection framework under class-imbalanced conditions based on improved you only look once network. Engineering Applications of Artificial Intelligence, 2024, 138(PA): 109351. DOI: 10.1016/J.ENGAPPAI.2024.109351.

[5] Anonymous. Enhancing Rail Integrity: Expansion of the Rail Flaw Library at the Transportation Technology Center. Railway Track & Structures, 2024, 120(9): 4-7.

[6] Chang Yongqi, Shen Yi, Zhang Xin, et al. Defect detection of ferromagnetic rail using EMAE-based peak-to-peak method and confidence probability indicator. Measurement Science and Technology, 2024, 35(1). DOI: 10.1088/1361-6501/AD006B.

[7] Santur Y, Yilmazer M, Karakose M, et al. A New Rail Surface Defects Detection Approach Using 3D Laser Cameras Based on ResNet50. Traitement du Signal, 2022, 39(4): 1339-1345. DOI: 10.18280/TS.390427.

[8] Zhao Y, Sun J H, Ma J, et al. Application of the hybrid laser ultrasonic method in rail inspection. INSIGHT, 2014, 56(7): 360-366. DOI: 10.1784/INSI.2014.56.7.360.