测绘通报 ›› 2021, Vol. 0 ›› Issue (8): 88-92.doi: 10.13474/j.cnki.11-2246.2021.0247

• 轨道交通前沿测绘技术研究与应用 • 上一篇    下一篇

轨道扣件病害自动化检测研究及应用

侯海倩1,2, 唐超1,2, 赵丽凤1,2, 张昊3   

  1. 1. 北京城建勘测设计研究院有限责任公司, 北京 100101;
    2. 城市轨道交通深基坑岩土工程北京市重点实验室, 北京 100101;
    3. 北京路桥瑞通养护中心有限公司, 北京 101300
  • 收稿日期:2021-06-07 修回日期:2021-06-24 出版日期:2021-08-25 发布日期:2021-08-30
  • 作者简介:侯海倩(1989-),女,硕士,工程师,主要从事轨道交通安全运营管理研究。E-mail:houkjz1989@163.com

Research and application of automatic detection of rail fastener damage

HOU Haiqian1,2, TANG Chao1,2, ZHAO Lifeng1,2, ZHANG Hao3   

  1. 1. Beijing Urban Construction Exploration & Surveying Design Research Institute Co., Ltd., Beijing 100101, China;
    2. Beijing Key Laboratory of Deep Foundation Pit Geotechnical Engineering of Rail Transit, Beijing 100101, China;
    3. Beijing Luqiao Ruitong Maintenance Center Co., Ltd., Beijing 101300, China
  • Received:2021-06-07 Revised:2021-06-24 Online:2021-08-25 Published:2021-08-30

摘要: 传统扣件检查基本采用人工检查方式,不仅工作效率低、劳动强度大,而且人为干扰因素多、检查采样率低。针对以上问题,本文提出了一种基于线结构光传感器的轨道扣件损伤和松动检测方法,并开发了轨道扣件智能监测系统以实现扣件病害自动检测。最终将研究成果应用于徐州市某地铁区间轨道扣件检测,验证了该方法的可行性和准确率,为地铁轨道扣件检查提供了新方法。

关键词: 轨道, 自动化检测, 结构光传感器, 扣件损伤, 决策树, 区域生长法

Abstract: The traditional fastener inspection basically adopts manual inspection method, which not only has the disadvantages of low work efficiency and high labor intensity, but also has the disadvantages of many human factors interference and low inspection sampling rate. To solve these problems, this paper proposes a method for detecting damage and loosening of rail fasteners based on a line structure light sensor, and develops an intelligent monitoring system for rail fasteners to realize detecting damage automatically. Finally, the research results are applied to the detection of rail fasteners in a subway section of Xuzhou city, and the method is verified with feasibility and accuracy, which provides a new method for the inspection of subway track fasteners.

Key words: rail, automatic detection, structured light sensor, fastener damage, decision tree, zone growing method

中图分类号: