Page 107 - 无损检测2024年第九期

试验研究
试验研究

DOI：10.11973/wsjc240106

基于多模态特征的重载铁路钢轨损伤检测方法

马 骞
（国能朔黄铁路发展有限责任公司肃宁分公司，肃宁 062350）

摘 要：列车重载运行的情况下钢轨会出现损伤，传统的钢轨损伤检测方法主要依靠人工巡检
或使用单一模态特征进行分析，存在准确性低、易漏检漏报等问题。针对这一问题，提出了基于多
模态特征的重载铁路钢轨损伤检测方法。首先采集重载铁路钢轨损伤图像，并以直方图均衡化的
增强方式预处理原始图像；然后将图像中的信息转换为模态向量进行特征提取，选择置信度矩阵表
示不同特征的分布情况，并分解钢轨损伤图像中的特征模态元素；最后基于多模态特征，关联具有
相关性的损伤特征模量，标注损失特征标签，实现重载钢轨损伤情况的判断和检测。分别以5 000，
10 000，30 000 t重载量级的铁路钢轨作为对象进行测试，试验结果表明，所提方法能够实现精准的
损伤定位，且对不同量级钢轨的损伤情况均具有较高检测精度，具有实际应用价值。
关键词：重载铁路；置信度矩阵；多模态特征；钢轨损伤；损伤检测
中图分类号：TP311；TG115.28 文献标志码：A 文章编号：1000-6656(2024)09-0069-06

Damage detection method of heavy duty railway rail based on multimodal features

MA Qian
（Suning Branch of Guoneng Shuozhou-Huanghua Railway Development Co., Ltd., Suning 062350, China）
Abstract: The rail will be damaged when the train is under heavy load operation. The traditional rail damage
detection methods mainly rely on manual inspection or use of single modal characteristics for analysis, which has
problems such as low accuracy, missing detection and reporting. Therefore, research is conducted on the detection
method of rail damage in heavy-duty railways based on multimodal features. Firstly, images of rail damage in
heavy-duty railways are collected, and the original images are preprocessed using histogram equalization. Then, the
information in the image is transformed into modal vectors for feature extraction. The confidence matrix is selected
to represent the distribution of different features in the image, and the feature modal elements in the rail damage
image are decomposed. Finally, based on multimodal features, correlated damage feature moduli with correlation are
annotated with loss feature labels to achieve the judgment and detection of heavy-duty rail damage. The experimental
results showed that the proposed method can accurately located the damage location and had high detection accuracy
for different levels of rail damage, with 5 000, 10 000，30 000 t heavy-duty railway rails as the test objects. It has
practical application value.
Key words: heavy haul railway; confidence matrix; multimodal feature; rail damage; damage detection

铁路具有运输承载力强和运输成本低等显著特 路承载量和运行强度逐渐加大，伴随列车运行时间
征，其在大流量和较长的客运和货运中均具有较大 的累积，列车会对铁路钢轨造成不同程度的损伤，例
优势。现阶段，人们的出行与运输需求不断增加，铁 如钢轨磨损、裂纹、变形等 [1-2] 。损伤一旦到达某个
临界点，会对列车造成颤动影响，带来安全隐患。为
此，需要对铁路钢轨的运行情况进行实时跟踪，并对
收稿日期：2024-03-13
作者简介：马 骞（1982—），男，硕士研究生，高级工程师，主要研 其损伤情况进行有效检测。文章以多模态特征方式
究方向为重载铁路养护与检测技术 为基础，提出重载铁路钢轨的损伤检测方式，为铁路
通信作者：马 骞，longquan198@126.com 的运行安全提供理论支持。
69
2024 年 第 46 卷 第 9 期
无损检测