轨道交通基础设施自主无人机智能巡检技术现状与发展趋势

doi:10.3969/j.issn.1673-4440.2025.02.001

铁路通信信号工程技术 ›› 2025, Vol. 22 ›› Issue (2): 1-10.DOI: 10.3969/j.issn.1673-4440.2025.02.001

• • 下一篇

轨道交通基础设施自主无人机智能巡检技术现状与发展趋势

秦勇^1，2，张紫城^1，2，杨怀志^3，4，孟凡腾^1，2，崔京^1，2，仇宁海^1，2，孟彤^1，2，刘鹏帅^1，2，汪洋^1，2，王志鹏^1，2

1．北京交通大学先进轨道交通自主运行全国重点实验室，北京 100044；
2．运营主动安全保障与风险防控铁路行业重点实验室，北京 100044;
3．京沪高速铁路股份有限公司，北京 100038;
4．京福铁路客运专线安徽有限责任公司，合肥 230031

收稿日期:2025-01-09 修回日期:2025-02-10 出版日期:2025-02-25 发布日期:2025-02-25
基金资助:
国家重点研发计划项目（2022YFB4300600）；先进轨道交通自主运行全国重点实验室自主研究课题项目（RAO2023ZZ003）；京沪高速铁路股份有限公司科技研究项目（京沪科研-2024-16）

Current Status and Development Trends of Autonomous UAV Intelligent Inspection Technology for Railway Infrastructure

Qin Yong^{1, 2}, Zhang Zicheng^{1, 2}, Yang Huaizhi^{3, 4}, Meng Fanteng^{1, 2}, Cui Jing^{1, 2}, Qiu Ninghai^{1, 2}, Meng Tong^{1, 2}, Liu Pengshuai^{1, 2}, Wang Yang^{1, 2}, Wang Zhipeng^{1, 2}

1. State Key Laboratory of Advanced Rail Autonomous Operation, Beijing Jiaotong University, Beijing 100044, China；
2. Key Laboratory of Railway Industry of Proactive Safety and Risk Control, Beijing Jiaotong University, Beijing 100044, China；
3. Beijing-Shanghai High Speed Railway Co., Ltd., Beijing 100038, China；
4. Beijing-Fuzhou Passenger Dedicated Railway Line Anhui Co., Ltd., Hefei 230031, China

Received:2025-01-09 Revised:2025-02-10 Online:2025-02-25 Published:2025-02-25

摘要/Abstract

摘要： 轨道交通既有基础设施服役时间增长，受环境和自然灾害影响性能劣化，病害频发，需先进巡检技术掌握其服役状态。现有机械与传感设备巡检存在频率低、覆盖范围有限、智能分析能力不足等问题，在桥梁、隧道口等区域巡检盲区多。无人机巡检具有高空作业、远距离覆盖、受地形与天窗限制小的优势。围绕轨道交通无人机智能巡检分析系统的 “边云协同” 分布式架构，探讨边缘端技术、云端技术及智能分析模型协同优化轨道基础设施巡检任务的方式，通过实际工程应用案例验证该技术的巡检价值，并基于无人机系统自主化等级，对未来无人机技术在轨道交通基础设施巡检中的潜在应用场景和研究方向进行展望。

关键词: 轨道交通基础设施, 自主无人机, 智能巡检, 边云协同

Abstract: With the extended service life of existing railway infrastructure, its performance deteriorates due to the impact of the environment and natural disasters, resulting in frequent damages. Advanced inspection technologies are required to comprehensively monitor its service status. Current mechanical and sensor-assisted inspection methods have problems such as low inspection frequency, limited coverage, and insufficient intelligent analysis capabilities. There are many inspection blind spots in areas like bridges, tunnel entrances, etc. UAV inspection has advantages such as aerial operation, long-distance coverage, and less restriction by terrain and construction windows. This paper focuses on the "edge-cloud collaboration" distributed architecture of the UAV intelligent inspection analysis system for rail transport. It explores how edge-end technologies, cloud technologies, and intelligent analysis models collaborate to optimize the inspection tasks of railway infrastructure. The inspection value of this technology is verified through practical engineering application cases. Based on the autonomy level of the UAV system, the potential application scenarios and research directions of future UAV technologies in the inspection of railway infrastructure are envisioned.

Key words: railway infrastructure, autonomous unmanned aerial vehicles, intelligent inspection, edge-cloud collaboration

中图分类号:

秦勇, 张紫城, 杨怀志, 孟凡腾, 崔京, 仇宁海, 孟彤, 刘鹏帅, 汪洋, 王志鹏. 轨道交通基础设施自主无人机智能巡检技术现状与发展趋势[J]. 铁路通信信号工程技术, 2025, 22(2): 1-10.

Qin Yong, Zhang Zicheng, Yang Huaizhi, Meng Fanteng, Cui Jing, Qiu Ninghai, Meng Tong, Liu Pengshuai, Wang Yang, Wang Zhipeng. Current Status and Development Trends of Autonomous UAV Intelligent Inspection Technology for Railway Infrastructure[J]. Railway Signalling & Communication Engineering, 2025, 22(2): 1-10.

图/表 5

参考文献

[1]刘伶萍，魏世斌，赵延峰，等.GJ-6型轨道检测系统的研制与验证[J].铁路技术创新，2015（2）：53-56.
[2]李耀云，高英杰，张文雍.高速铁路供电安全检测监测系统(6C系统)分析方法探讨[J].电气化铁道，2019，30（Z1）：205-208.
[3]谭远鑫，呙润华，施鹏程.基于车载式激光雷达的隧道变形动态巡检技术研究[J].城市轨道交通研究，2024，27（6）：276-280，285.
Tan Yuanxin, Guo Runhua, Shi Pengcheng. Dynamic Inspection Technology of Tunnel De-Formation Based on Onboard LIDAR[J]. Urban Mass Transit, 2024, 27(6): 276-280, 285.
[4]梁志雯，李小波，张吉.桥梁巡检机器人发展与应用现状探讨[J].产业科技创新，2024（5）：66-70.
Liang Zhiwen, Li Xiaobo, Zhang Ji. Development and Application Status of Bridge Inspection Robots[J]. Industrial Technology Innovation, 2024(5): 66-70.
[5]秦暄阳，张喆，王浩宇，等.国内外铁路巡检无
人机应用现状分析(下)[J].铁道技术监督， 2024，52（2）：53-57.
Qin Xuanyang, Zhang Zhe, Wang Haoyu, et al. Analysis on the Application Status of Railway Inspection Unmanned Aerial Vihicle at Home and Abroad(Part 2 of 2)[J]. Railway Quality Control, 2024, 52(2): 53-57.
[6]蔡伯根，李智宇，王剑，等.面向铁路巡检的低空无人机智能感知与精密定位研究[J].铁路通信信号工程技术，2025，22（1）：1-12.
Cai Baigen, Li Zhiyu, Wang Jian, et al. Research on Intelligent Sensing and Precise Positioning of Low-Altitude UAV for Railway Inspection[J]. Railway Signalling & Communication Engineering, 2025, 22(1): 1-12.
[7]赵强，刘志明.无人机在铁路行业的应用探索与实践[J].铁路通信信号工程技术，2025，22（1）： 13-18.
Zhao Qiang, Liu Zhiming. Application Exploration and Practice of UAVs in Railways[J]. Railway Signalling & Communication Engineering, 2025, 22(1): 13-18.
[8]秦暄阳，张喆，王浩宇，等.国内外铁路巡检无
人机应用现状分析(上)[J].铁道技术监督，2024，52（1）：48-51，55.
Qin Xuanyang, Zhang Zhe, Wang Haoyu, et al. Analysis on the Application Status of Railway Inspection Unmanned Aerial Vihicle at Home and Abroad(Part 1 of 2)[J]. Railway Quality Control, 2024, 52(1): 48-51, 55.
[9] Wu Yunpeng, Qin Yong, Wang Zhipeng, et al. A UAV-Based Visual Inspection Method for Rail Surface Defects[J]. Applied Sciences, 2018, 8(7): 1028.
[10] Wu Yunpeng, Qin Yong, Qian Yu, et al. Hybrid Deep Learning Architecture for Rail Surface Segmentation and Surface Defect Detection[J]. Computer-Aided Civil and Infrastructure Engineering, 2022, 37(2): 227-244.
[11] Wu Yunpeng, Chen Ping, Qin Yong, et al. Automatic Railroad Track Components Inspection Using Hybrid Deep Learning Framework[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 5011415.
[12] Wu Yunpeng, Qin Yong, Qian Yu, et al. Automatic Detection of Arbitrarily Oriented Fastener Defect in High-Speed Railway[J]. Automation in Construction, 2021, 131: 103913.
[13] Wu Yunpeng, Meng Fanteng, Qin Yong, et al. Automated Anomaly Detection of Catenary Split Pins Using Unsupervised Learning[J]. Automation in Construction, 2024, 165: 105589.
[14] Meng Fanteng, Qin Yong, Wu Yunpeng, et al. A Subtle Defect Recognition Method for Catenary Fastener in High-Speed Railroad Using Destruction and Reconstruction Learning[J]. Advanced Engineering Informatics, 2024, 60: 102393.
[15] Cui Jing, Qin Yong, Wu Yunpeng, et al. Skip Connection YOLO Architecture for Noise Barrier Defect Detection Using UAV-Based Images in High-Speed Railway[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(11): 12180-12195.
[16] Mu Zonghan, Qin Yong, Yu Chongchong, et al. Adaptive Cropping Shallow Attention Network for Defect Detection of Bridge Girder Steel Using Unmanned Aerial Vehicle Images[J]. Journal of Zhejiang University: Science A, 2023, 24(3): 243-256.
[17] Wu Yunpeng, Zhao Zheda, Chen Ping, et al. Hybrid Learning Architecture for High-Speed Railroad Scene Parsing and Potential Safety Hazard Evaluation of UAV Images[J]. Measurement, 2025, 239: 115504.
[18] Zhao Zheda, Qin Yong, Qian Yu, et al. Automatic Potential Safety Hazard Evaluation System for Environment around High-Speed Railroad Using Hybrid U-Shape Learning Architecture[J]. IEEE Transactions on Intelligent Transportation Systems, 2025, 26(1): 1071-1087.
[19] Wu Yunpeng, Meng Fanteng, Qin Yong, et al. UAV Imagery Based Potential Safety Hazard Evaluation for High-Speed Railroad Using Real-Time Instance Segmentation[J]. Advanced Engineering Informatics, 2023, 55: 101819.
[20] Wang Zhipeng, Geng Yixuan, Jia Limin, et al. Self-Attentive Local Aggregation Learning with Prototype Guided Regularization for Point Cloud Semantic Segmentation of High-Speed Railways[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(10): 11157-11170.
[21] Geng Yixuan, Pan Fengjun, Jia Limin, et al. UAV-LiDAR-Based Measuring Framework for Height and Stagger of High-Speed Railway Contact Wire[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(7): 7587-7600.
[22]秦勇，邵长虹，杨怀志，等.京沪高铁基础设施无人机智能巡检系统关键技术[J].中国铁路，2024（4）：15-21.
Qin Yong, Shao Changhong, Yang Huaizhi, et al. Key Technologies of UAV Intelligent Patrol Inspection System for Beijing-Shanghai HSR Infrastructure[J]. China Railway, 2024(4): 15-21.
[23]田元.搭载无线LoRa网络设备的倾转旋翼无人机在轨道巡检和救灾中的应用研究[J].铁路通信信号工程技术，2017，14（5）：69-70，92.
Tian Yuan. Research on Application of Tilt-Wing UAV with Wireless Lo Ra Network Equipment in Track Inspection and Disaster Rescue[J]. Railway Signalling & Communication Engineering, 2017, 14(5): 69-70, 92.
[24]中国民用航空局.民用无人驾驶航空器系统分布式操作运行等级划分：MH/T 2013-2022[S].北京:中国民航出版社，2022.
[25]潘泉，郭亚宁，吕洋，等.无人机系统自主安全:定义、建模与分级[J].中国科学:信息科学，2023，53（8）：1608-1628.
Pan Quan, Guo Yaning, Lv Yang, et al. Autonomous Safety and Security of UAV Systems:Definition,Modeling,and Gradation[J]. Scientia Sinica (Informationis), 2023, 53(8): 1608-1628.

轨道交通基础设施自主无人机智能巡检技术现状与发展趋势

Current Status and Development Trends of Autonomous UAV Intelligent Inspection Technology for Railway Infrastructure

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	李广智, 李飞, 黄志伟, 李达明, 陈柯行, 蒙笑阳, 吴昊. 编组站无人机智能巡检调度系统研究[J]. 铁路通信信号工程技术, 2025, 22(2): 18-23,83.
[2]	赵强, 刘志明. 无人机在铁路行业的应用探索与实践[J]. 铁路通信信号工程技术, 2025, 22(1): 13-18.