基于线结构光的钢轨断面磨耗改进检测算法

刘震锋; 陈建政; 李伟

doi:10.13890/j.issn.1000-128X.2024.03.017

您当前的位置：

首页 >

文章列表页 >

基于线结构光的钢轨断面磨耗改进检测算法

智能化技术 | 更新时间：2024-08-01

- 基于线结构光的钢轨断面磨耗改进检测算法
- Improved detection algorithm for rail profile wear based on line structured light
- 机车电传动 2024年第3期页码：138-145
- 作者机构：
  
  西南交通大学轨道交通运载系统全国重点实验室，四川成都 610031
- 作者简介：
  
  陈建政，男，研究员，硕士研究生导师，主要从事机车车辆动态检测技术及数据处理，机车车辆故障诊断及安全检测等研究； E-mail: chenjzh@home.swjtu.edu.cn
- 基金信息：
  
  四川省自然科学基金项目(24NSFSC0307)
- DOI：10.13890/j.issn.1000-128X.2024.03.017
  中图分类号： U213.4⁺2
- 纸质出版日期：2024-05-10，
  
  收稿日期：2023-12-29，
  
  修回日期：2024-05-01，
- 稿件说明：
扫描看全文
刘震锋, 陈建政, 李伟. 基于线结构光的钢轨断面磨耗改进检测算法[J]. 机车电传动, 2024(3): 138-145.

LIU Zhengfeng, CHEN Jianzheng, LI Wei. Improved detection algorithm for rail profile wear based on line structured light[J]. Electric drive for locomotives,2024(3): 138-145.
刘震锋, 陈建政, 李伟. 基于线结构光的钢轨断面磨耗改进检测算法[J]. 机车电传动, 2024(3): 138-145. DOI：10.13890/j.issn.1000-128X.2024.03.017.

LIU Zhengfeng, CHEN Jianzheng, LI Wei. Improved detection algorithm for rail profile wear based on line structured light[J]. Electric drive for locomotives,2024(3): 138-145. DOI：10.13890/j.issn.1000-128X.2024.03.017.

摘要

经典的最近点迭代（Iterative Closest Point

ICP）配准算法常被应用于钢轨断面磨耗检测系统。当轨道检修车工作运行时，基于线结构光的钢轨断面磨耗检测系统采集的钢轨廓形数据通常会受到各种离群点噪声的干扰，导致计算得到的钢轨廓形几何形态变化较大。在实际应用中，轨道检修车钢轨断面磨耗动态检测精度要求侧磨为±0.5 mm，垂磨为±1.0 mm，故磨耗检测算法的设计不能因为廓形含离群点噪声而降低检测精度。因此，文章提出了一种改进的两阶段钢轨断面廓形磨耗检测算法。该算法在第一阶段首先利用钢轨廓形的特征点对进行快速初始配准，使得2个点云集具有较好的初始位姿，第二阶段采用改进的鲁棒ICP算法完成精确配准，最后计算得到钢轨断面磨耗几何参数。通过在实验室搭建钢轨断面磨耗检测系统试验平台，以试验模拟实测数据常见的轨腰段和轨底段离群点干扰，并以手工接触式磨耗仪的测量数据作为参考基准，对比经典ICP算法和文章所提出的改进算法，分析磨耗检测的精度误差和有效性，并在此基础上，对算法的检测速度进行对比分析，对改进算法的重复性测量精度进行验证，最后在地铁线路上开展轨道检修车实测验证。结果表明，文章所提的改进算法有效提高了在离群点干扰场景下钢轨断面磨耗检测的精度和速度，具有工程实用价值。

Abstract

The classical Iterative Closest Point (ICP) registration algorithm is commonly applied to rail profile wear detection systems. However

during the operation of track inspection vehicles

the profile data collected by the rail profile wear detection system based on linear structured light is often disrupted by noise from various outliers

leading to significant geometric variations in the rail profile calculation results. Given the dynamic detection accuracy requirements for rail profile wear using track inspection vehicles of ±0.5 mm for lateral wear and ±1.0 mm for vertical wear in practical applications

it is crucial that the design of wear detection algorithms do not compromise the detection accuracy due to outlier-induced noise in the profile data. To address this

this paper presented an improved two-stage rail profile wear detection algorithm. In the first stage

this algorithm enabled rapid initial registration based on feature point pairs extracted from the rail profile

providing an improved initial pose for the two point clouds. The second stage utilized an enhanced robust ICP algorithm for precise registration

followed by calculating geometric parameters related to rail profile wear. A laboratory experimental platform was set up to evaluate the developed rail profile wear detection system. This setup simulated typical disruptions from outliers in the measured data of rail web and rail base segments

in comparison with the measurements obtained using a manual contact-type wear tester for benchmarking. Moreover

the accuracy errors and effectiveness of wear detection were analyzed by comparing the classical ICP algorithm and articles with the proposed improved algorithm. Furthermore

a comparative evaluation was conducted to examine the detection speed of the algorithms

and the accuracy in repeatability measurements using the improved algorithm was verified. Finally

validation was conducted on a metro line using a track inspection vehicle

and the results highlighted the enhanced accuracy and speed of rail profile wear detection based on the improved algorithm in scenarios with disruptions from outliers

demonstrating the practical engineering value of the proposed algorithm.

关键词

钢轨断面廓形配准钢轨磨耗特征点鲁棒ICP算法

Keywords

rail profileprofile registrationrail wearfeature pointsrobust ICP algorithm

references

陈经纬, 崔涛, 孙建锋, 等. 基于高速列车异常晃动的钢轨廓形打磨管理[J]. 机车电传动, 2020(5): 128-131.

CHEN Jingwei, CUI Tao, SUN Jianfeng, et al. Grinding management of rail profile based on abnormal hunting of high-speed train[J]. Electric drive for locomotives, 2020(5): 128-131.

孟佳, 高晓蓉. 钢轨磨耗检测技术的现状与发展[J]. 铁道技术监督, 2005(1): 34-36.

MENG Jia, GAO Xiaorong. Current status and development of rail wear detection technology[J]. Railway quality control, 2005(1): 34-36.

WANG Chao, LI Yanfu, MA Ziji, et al. Distortion rectifying for dynamically measuring rail profile based on self-calibration of multiline structured light[J]. IEEE transactions on instrumentation and measurement, 2018, 67(3): 678-689.

FRANCA J G D M, GAZZIRO M A, IDE A N, et al. A 3D scanning system based on laser triangulation and variable field of view[C]//IEEE. IEEE International Conference on Image Processing 2005. Genova: IEEE, 2005.

LIU Zhen, SUN Junhua, WANG Heng, et al. Simple and fast rail wear measurement method based on structured light[J]. Optics and lasers in engineering, 2011, 49(11): 1343-1351.

杨强, 林建辉, 丁建明, 等. 基于二维激光位移传感器和遗传算法的钢轨磨耗动态检测系统[J]. 中国铁路, 2012(6): 85-88.

YANG Qiang, LIN Jianhui, DING Jianming, et al. Dynamic rail wear detection system based on two-dimensional laser displacement sensor and genetic algorithm[J]. Chinese railways, 2012(6): 85-88.

孙军华, 王伟华, 刘震, 等. 基于结构光视觉的钢轨磨耗测量方法[J]. 北京航空航天大学学报, 2010, 36(9): 1026-1029.

SUN Junhua, WANG Weihua, LIU Zhen, et al. Rail wear measurement method based on structured-light vision[J]. Journal of Beijing university of aeronautics and astronautics, 2010, 36(9): 1026-1029.

徐晋卿, 陈唐龙, 占栋, 等. 基于机器视觉的钢轨轮廓测量方法研究[J]. 传感器与微系统, 2014, 33(4): 27-30.

XU Jinqing, CHEN Tanglong, ZHAN Dong, et al. Study of measurement method for rail profile based on machine vision[J]. Transducer and microsystem technologies, 2014, 33(4): 27-30.

王德明, 王桂宝, 张广明, 等. 基于激光轮廓扫描仪的钢轨磨耗检测系统[J]. 仪表技术与传感器, 2014(10): 90-91.

WANG Deming, WANG Guibao, ZHANG Guangming, et al. Rail wear detection system based on laser profile scanner[J]. Instrument technique and sensor, 2014(10): 90-91.

周志杰, 陈建政. 基于二维激光位移传感器的钢轨磨耗改进检测算法[J]. 传感器与微系统, 2019, 38(5): 133-135.

ZHOU Zhijie, CHEN Jianzheng. Improved rail wear detection algorithm based on two-dimensional laser displacement sensor[J]. Transducer and microsystem technology, 2019, 38(5): 133-135.

BESL P J, MCKAY N D. A method for registration of 3-D shapes[J]. IEEE transactions on pattern analysis and machine intelligence, 1992, 14(2): 239-256.

朱新荣, 郭振通, 周云霞, 等. 钢轨轮廓全断面检测中的匹配方法研究[J]. 铁道科学与工程学报, 2018, 15(9): 2401-2406.

ZHU Xinrong, GUO Zhentong, ZHOU Yunxia, et al. Research on matching algorithm in rail profile inspection[J]. Journal of railway science and engineering, 2018, 15(9): 2401-2406.

左伟, 李剑锋, 罗梓河. 一种基于叠加权重ICP的快速钢轨廓形匹配算法[J]. 控制与信息技术, 2023(5): 91-97.

ZUO Wei, LI Jianfeng, LUO Zihe. A fast rail profile registration algorithm based on weighted ICP[J]. Control and information technology, 2023(5): 91-97.

HOLLAND P W, WELSCH R E. Robust regression using iteratively reweighted least-squares[J]. Communications in statistics: theory and methods, 1977, 6(9): 813-827.

谢文军. GJ-6型轨检车检测系统原理及应用[M]. 北京: 中国铁道出版社, 2017.

XIE Wenjun. Principle and application of GJ-6 rail inspection vehicle detection system[M]. Beijing: China Railway Publishing House, 2017.

浏览量

下载量

CSCD

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于SIFT的高速列车车顶瓷瓶识别方法