[1]马 骏,薛 旭,陈秉智.基于 3D 扫描的高速铁路轮对踏面擦伤检测方法[J].机械与电子,2025,(11):47-53.
　MA Jun,XUE Xu,CHEN Bingzhi.A Method for Detecting Scratches on the Tread of High-speed Railway Wheelsets Based on 3D Scanning[J].Machinery & Electronics,2025,(11):47-53.
点击复制

基于 3D 扫描的高速铁路轮对踏面擦伤检测方法()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2025年11期
页码:
47-53
栏目:
自动控制与检测
出版日期:
2025-11-24

文章信息/Info

Title:
A Method for Detecting Scratches on the Tread of High-speed Railway Wheelsets Based on 3D Scanning
文章编号:
1001-2257 ( 2025 ) 11-0047-07
作者:
马 骏 1 ; 薛 旭 2 ; 陈秉智 1
1. 大连交通大学机械工程学院,辽宁 大连 116028 ;
2. 大连交通大学电气工程学院,辽宁 大连 116028
Author(s):
MA Jun1 ;  XUE Xu2 ;  CHEN Bingzhi1
( 1.School of Mechanical Engineering , Dalian Jiaotong University , Dalian 116028 , China ;
2.School of Electrical Engineering , Dalian Jiaotong University , Dalian 116028 , China )
关键词:
3D 扫描; 擦伤检测; 高斯核函数; 尺度空间;  DoG 函数; 偏移量; 对称操作; 多辨率分组
Keywords:
3D scanning ;  scratch detection ;  Gaussian kernel function ;  scale space ;  DoG function ;  offset ;  symmetric operation ;  multi-resolution grouping
分类号:
U238 ;TP3691.4
文献标志码:
A
摘要:
针对 3D 数据在离散与连续空间中多尺度处理导致极值点偏移量大,使得高速铁路轮对踏面擦伤面积分布映射结果与实际情况偏差较大的问题,提出基于 3D 扫描的高速铁路轮对踏面擦伤检测方法。利用高斯核函数构建高速铁路轮对踏面 3D 图像的尺度空间,通过 DoG 函数拟合局部关键点与尺度空间内的所有相邻像素点,校正极值点偏移量,输出 3D 图像的特征点云,避免了极值点偏移量的干扰。利用对称操作函数对特征点云进行高维映射后,根据多分辨率分组学习结果分割高速铁路轮对踏面 3D 数据中的擦伤语义。测试结果表明,所提方法在有效提取特征点云的基础上,能够实现对高速铁路轮对踏面擦伤的有效检测,擦伤面积分布与实际情况的偏差稳定在 0.1 cm2以内。
Abstract:
Aiming at the problem of large offset of extreme points caused by multi-scale processing of 3D data in discrete and continuous spaces , which leads to significant deviation between the mapping results of high-speed railway wheelset tread scratch area distribution and the actual situation , a high-speed railway wheelset tread scratch detection method based on 3D scanning is proposed.Using Gaussian kernel function to construct the scale space of high-speed railway wheelset tread 3D image , local key points are fitted with all adjacent pixel points in the scale space through DoG function , correcting the extreme point offset and outputting the feature point clouds of the 3D image to avoid the interference of extreme point offset.After using symmetric operation functions to perform high-dimensional mapping on feature point clouds , the scratch semantics in the 3D data of high-speed railway wheelset treads are segmented based on multi-resolution grouping learning results.The test results show that the proposed method can effectively detect the tread scratches of high-speed railway wheelsets based on the effective extraction of feature point clouds , and the deviation between the scratch area distribution and the actual situation is stable within 0.1 cm2 .

参考文献/References:

[ 1 ] 周素霞,李光,孙宇铎,等 . 重载机车不同轴序轮径差造成的踏面损伤规律[ J ] . 科学技术与工程, 2025 , 25 ( 2 ):780-787.

[ 2 ] 石珮廷,杨延峰,杨兴宽,等 .HXD2 型机车车轮踏面斜裂纹产生机制及旋修对策研究[ J ] . 铁道机车车辆,2024 , 44 ( 2 ): 130-137.
[ 3 ] 宋剑锋,时迎港,黄伟建,等 . 重载列车紧急制动过程踏面轮廓变化定量预测[ J ] . 中国机械工程, 2025 , 36 ( 2 ):369-379.
[ 4 ] 程翔,朱禹熹,贾林 . 基于多尺度可分离蒸馏网络的列车轮对踏面缺陷检测算法[ J ] . 铁道科学与工程学报,2024 , 21 ( 11 ): 4789-4803.
[ 5 ] 何静,黄聪聪,张昌凡,等 . 基于改进 SNN 的列车轮对踏面缺陷识别方法[ J ] . 铁道学报, 2025 , 47 ( 1 ): 91-100.
[ 6 ] 钱尚乐,曹伟,高军伟 . 基于改进 YOLOv7-tiny 的轻量化列车轮对踏面缺陷检测方法[ J ] . 光电子·激光,2025 , 36 ( 7 ): 733-744.
[ 7 ] 沈龙江,邓小星,陈国胜,等 . 速度 160 km / h 动力集中动车组动力车车轮踏面优化研究[ J ] . 铁道机车车辆,2024 , 44 ( 3 ): 125-131.
[ 8 ] LI Y L , LI M Y , TANG H.A crack detection method for civil engineering bridges based on feature extraction and parametric modeling of point cloud data [ J ] .Journal of computing and information technology , 2024 , 32( 2 ): 81-96.
[ 9 ] 黄奎龙,余刚,方修洋,等 . 踏面匹配与初始裂纹形态交互作用下车轮多轴疲劳裂纹扩展特性[ J ] . 材料导报,2024 , 38 ( 4 ): 191-195.
[ 10 ] 方鑫,刘通,程亚萍,等 . 基于 GA 岭回归分析的机车车轮踏面磨耗量预测算法研究[ J ] . 机车电传动, 2023( 6 ): 71-78.
[ 11 ] 张趁香,蒋建峰 . 基于机器视觉的复杂背景下车轮踏面损伤检测[ J ] . 计算机仿真, 2023 , 40 ( 10 ): 258-262.
[ 12 ] CHEN W J , LI C W , HUANG L Z , et al.GJFocuser : a Gaussian difference and joint learning-based autofocus method for whole slide imaging. [ J ] .Biomedical optics express , 2025 , 16 ( 1 ): 282-302.
[ 13 ] 刘应桃,郭世伟,付孟新,等 . 基于改进 Faster RCNN 的轮对踏面缺陷检测[ J ] . 电子测量技术,2023 , 46( 12 ): 34-41.
[ 14 ] 杨能普,周苗,王文昆,等 . 基于 R-P 图像注意融合网络的列车轮对踏面缺陷识别[ J ] . 铁道科学与工程学报,2023 , 20 ( 12 ): 4811-4822.

备注/Memo

备注/Memo:
收稿日期: 2025-06-18
作者简介:马 骏 ( 1990- ),男,辽宁大连人,博士,研究方向为智能传感与测控技术等,通信作者, E mail : whjunfei@163.com ;薛 旭 ( 1983- ),男,山西运城人,硕士,工程师,研究方向为综合自动化与先进控制技术等;陈秉智 ( 1971- ),男,浙江宁波人,博士,教授,研究方向为虚拟样机技术、多学科优化设计和生物力学等。
更新日期/Last Update: 2025-12-12