首页 > 论文 > 中国激光 > 47卷 > 11期(pp:1104006--1)

基于ROI-RSICP算法的车轮廓形动态检测

Dynamic Inspection of Wheel Profile Based on ROI-RSICP Algorithm

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

在车轮廓形动态检测过程中,线激光传感器只能安装在轨道旁作业,线激光测量平面与车轮表面交线无法通过车轮轮心,导致采集到的大量车轮廓形数据存在仿射畸变,难以用传统迭代最近邻(ICP)算法进行准确匹配,测量精确性与鲁棒性难以保证。提出了一种基于感兴趣域的加权尺度迭代最近邻 (ROI-RSICP) 算法,对存在仿射畸变的磨耗车轮廓形实现了精确测量。首先,根据车轮廓形磨耗特征和大量磨耗车轮数据,采用PointNet深度学习网络,将采集的车轮廓形点集分成磨耗感兴趣区域(ROI)和非磨耗区域;然后,通过对磨耗ROI和非磨耗区域赋予不同权重值,提出了ROI-RSICP方法,并实现了仿射畸变磨耗车轮廓形与标准廓形的精确配准;最后,通过Hausdorff距离算法实现了车轮磨耗可视化处理。实验对比了ICP算法、Scaling ICP算法、ROI-RSICP算法以及第四种检查器的测量结果,验证了所提算法对仿射畸变磨耗车轮廓形动态检测的可行性。

Abstract

As the line laser sensor can be only installed beside rails during dynamic inspection, it cannot ensure the intersection line of line laser measurement plane and wheel surface to be through wheel center, which causes the affine distortion of large number of wheel profiles and makes it difficult to use the traditional iterative closest point (ICP) algorithm to register the measured profile and to ensure the accuracy and robustness of measurement. In this paper, an algorithm of reweighted scaling iterative closest point based on region of interest (ROI-RSICP) is proposed to achieve accurate registration of worn wheel profiles with affine distortion. First, according to the wear characteristics of wheel profiles and a large number of worn wheel profile data, the PointNet deep learning network is adopted to divide the collected wheel profile point sets into two parts: wear region of interest (ROI) and non-wear part. Then, the ROI-RSICP method is proposed by assigning different values of weight to ROI and non-wear part to achieve accurate registration of the worn wheel profiles with affine distortion and the standard wheel profiles. Finally, the Hausdorff distance algorithm is used to visualize the wheel profile wear. The results of ICP algorithm, scaling ICP algorithm, ROI-RSICP algorithm and the 4th kind of inspector are compared in the experiment, which verifies the superiority of the proposed algorithm for dynamic inspection of worn wheel profiles with affine distortion.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:O436

DOI:10.3788/CJL202047.1104006

所属栏目:测量与计量

基金项目:国家自然科学基金面上基金 、湖南省自然科学基金 、中南大学中央高校基本科研业务费专项资金;

收稿日期:2020-06-04

修改稿日期:2020-07-06

网络出版日期:2020-11-01

作者单位    点击查看

易倩:中南大学交通运输工程学院, 湖南 长沙 410075
钟浩宇:中南大学交通运输工程学院, 湖南 长沙 410075
刘龙:中南大学交通运输工程学院, 湖南 长沙 410075
刘文龙:中南大学交通运输工程学院, 湖南 长沙 410075汉阳大学机械工程学院, 首尔04763, 韩国
易兵:中南大学交通运输工程学院, 湖南 长沙 410075

联系人作者:易兵(bingyi@csu.edu.cn)

备注:国家自然科学基金面上基金 、湖南省自然科学基金 、中南大学中央高校基本科研业务费专项资金;

【1】Zhang H B, Ye H J. Researching of inspecting method for wheelsets abrasion based on image processing [J]. Machinery. 2004, 31(8): 51-53.
张红波, 叶海建. 基于图像处理的轮对磨耗值检测方法的研究 [J]. 机械. 2004, 31(8): 51-53.
Zhang H B, Ye H J. Researching of inspecting method for wheelsets abrasion based on image processing [J]. Machinery. 2004, 31(8): 51-53.
张红波, 叶海建. 基于图像处理的轮对磨耗值检测方法的研究 [J]. 机械. 2004, 31(8): 51-53.

【2】Feng Q B, Chen S. New method for automatically measuring geometric parameters of wheel sets by laser [J]. Proceedings of SPIE. 2003, 5253: 110-113.

【3】Torabi M. Mousavi S G M, Younesian D. A high accuracy imaging and measurement system for wheel diameter inspection of railroad vehicles [J]. IEEE Transactions on Industrial Electronics. 2018, 65(10): 8239-8249.

【4】Chen H, Zhang S J, Gao J, et al. Online three-dimensional measurement technology for steel wheel based on rotating scanning of multiple line-laser sensors [J]. Chinese Journal of Lasers. 2019, 46(7): 0704006.
陈瀚, 张思瑾, 高见, 等. 基于多个线激光传感器旋转扫描的铸钢车轮在线三维测量技术 [J]. 中国激光. 2019, 46(7): 0704006.

【5】Li M C, Yang Y, Yi B, et al. Radius constraint iteratively reweighted least squares circle fitting method and its application in line laser-based wheel tread detection [J]. Chinese Journal of Lasers. 2020, 47(9): 0904005.
李淼成, 杨岳, 易兵, 等. RC-IRLSCF方法及其服役车轮踏面线激光检测应用 [J]. 中国激光. 2020, 47(9): 0904005.

【6】Zhang Z F, Lu C, Zhang F Z, et al. A Novel Method for non-contact measuring diameter parameters of wheelset based on wavelet analysis [J]. Optik. 2012, 123(5): 433-438.

【7】Zhang Z F, Su Z, Su Y L, et al. Denoising of sensor signals for the flange thickness measurement based on wavelet analysis [J]. Optik. 2011, 122(8): 681-686.Zhang Z F, Su Z, Su Y L, et al. Denoising of sensor signals for the flange thickness measurement based on wavelet analysis [J]. Optik. 2011, 122(8): 681-686.

【8】Chen X M, Sun J H, Liu Z, et al. Dynamic tread wear measurement method for train wheels against vibrations [J]. Applied Optics. 2015, 54(17): 5270-5280.

【9】Xing Z Y, Chen Y J, Wang X H, et al. Online detection system for wheel-set size of rail vehicle based on 2D laser displacement sensors [J]. Optik. 2016, 127(4): 1695-1702.

【10】Gao Y, Feng Q B, Cui J Y. A simple method for dynamically measuring the diameters of train wheels using a one-dimensional laser displacement transducer [J]. Optics and Lasers in Engineering. 2014, 53: 158-163.

【11】Cheng X Q, Chen Y J, Xing Z Y, et al. A novel online detection system for wheelset size in railway transportation [J]. Journal of Sensors. 2016, 2016: 9507213.

【12】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.

【13】Hou B, Jin S Z, Wang Y, et al. Comparison of point cloud registration methods in coarse registration [J]. Laser & Optoelectronics Progress. 2020, 57(8): 081502.
侯彬, 金尚忠, 王赟, 等. 点云配准方法在粗配准中的比较 [J]. 激光与光电子学进展. 2020, 57(8): 081502.

【14】Wang C, Shu Q, Yang Y X, et al. Point cloud registration in multidirectional affine transformation with variance compensation [J]. Acta Optica Sinica. 2019, 39(2): 0215002.
王畅, 舒勤, 杨赟秀, 等. 带方差补偿的多向仿射变换点云配准算法 [J]. 光学学报. 2019, 39(2): 0215002.

【15】Du S Y, Zheng N N, Xiong L, et al. Scaling iterative closest point algorithm for registration of m-D point sets [J]. Journal of Visual Communication and Image Representation. 2010, 21(5/6): 442-452.

【16】Tang Z R, Liu M Z, Jiang Y, et al. Point cloud registration algorithm based on canonical correlation analysis [J]. Chinese Journal of Lasers. 2019, 46(4): 0404006.
唐志荣, 刘明哲, 蒋悦, 等. 基于典型相关分析的点云配准算法 [J]. 中国激光. 2019, 46(4): 0404006.

【17】A novel method for automatically measuring wheel geometric parameters by laser scanning [J]. Chinese Journal of Lasers. 2013, 40(7): 0708005.
高岩, 邵双运, 冯其波. 一种激光扫描自动测量轮对几何参数的方法 [J]. 中国激光. 2013, 40(7): 0708005.

【18】Yan J M, Fu M H. Vehicle engineering[M]. Beijing: China Railway Publishing House, 2008, 37-50.
严隽耄, 傅茂海. 车辆工程[M]. 3版. 北京: 中国铁道出版社, 2008, 37-50.

【19】Yang Y, Liu L, Yi B, et al. Dynamic inspection of a rail profile under affine distortion based on the reweighted-scaling iterative closest point method [J]. Measurement Science and Technology. 2019, 30(11): 115202.

【20】Yang Y, Liu L, Li M C, et al. Sparse scaling iterative closest point for rail profile inspection [J]. Journal of Computing and Information Science in Engineering. 2019, 20(1): 011003.

【21】Charles R Q, Su H, Mo K C, et al. PointNet: deep learning on point sets for 3D classification and segmentation . [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 2017, 77-85.

【22】Bergstr?m P, Edlund O. Robust registration of point sets using iteratively reweighted least squares [J]. Computational Optimization and Applications. 2014, 58(3): 543-561.

【23】Sorkine O, Alexa M. As-rigid-as-possible surface modeling . [C]∥Proceedings of the Fifth Eurographics Symposium on Geometry Processing (SGP), July 4-6, 2007, Barcelona, Spain. Demark: ACM. 2007, 109-116.

【24】Arun K S, Huang T S, Machine Intelligence. PAMI- . 1987, 9(5): 698-700.

【25】Yang Y, Liu L, Yi B, et al. An accurate and fast method to inspect rail wear based on revised global registration [J]. IEEE Access. 2018, 6: 57267-57278.

【26】Huttenlocher D P, Klanderman G A, Rucklidge W J. Comparing images using the Hausdorff distance [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1993, 15(9): 850-863.

【27】Alberto G G, Sergio O E, Sergiu O, et al. -08-22) [2020-05-29] . https:∥arxiv.org/pdf/1704.06857.pdf. 2017.

引用该论文

Yi Qian,Zhong Haoyu,Liu Long,Liu Wenlong,Yi Bing. Dynamic Inspection of Wheel Profile Based on ROI-RSICP Algorithm[J]. Chinese Journal of Lasers, 2020, 47(11): 1104006

易倩,钟浩宇,刘龙,刘文龙,易兵. 基于ROI-RSICP算法的车轮廓形动态检测[J]. 中国激光, 2020, 47(11): 1104006

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF