基于灰度-梯度共生矩阵的车轮踏面缺陷聚类分析  

Cluster analysis of wheel tread defects based on gray-gradient cooccurrence matrix

作　　者：刘二林[1] 刘成刚 姜香菊[2] 杨尚梅 LIU Erlin;LIU Chenggang;JIANG Xiangju;YANG Shangmei(Schoolof Mechanical and Electrical Engineering,Lanzhou Jiaotang University,Lanzhou.Gansu730070,China;School of Automation and Elctrical Engineering,Lanzhou Jiaotong University,Lanzhou,Gansu 730070,China;School of Electrical Engineering,Lanzhou Institute of Technology,Lanzhou.Gansu 730000,China)

机构地区：[1]兰州交通大学机电工程学院,甘肃兰州730070 [2]兰州交通大学自动化与电气工程学院,甘肃兰州730070 [3]兰州工业学院电气工程学院,甘肃兰州730000

出　　处：《光电子．激光》2022年第1期53-60,共8页Journal of Optoelectronics·Laser

基　　金：甘肃省兰州市人才创新创业项目(2020-RC-105)资助项目。

摘　　要：车轮作为列车走行部的关键部件之一,其踏面产生缺陷后会直接影响到列车的运行安全。为了能够在检测时准确识别车轮踏面缺陷不同类型,提出一种基于灰度-梯度共生矩阵的纹理特征提取方法,对踏面图像的灰度和梯度特征分析之后,根据灰度-梯度共生矩阵提取踏面图像纹理特征矢量,再结合K-均值(K-means)聚类优化算法对踏面缺陷特征量进行聚类,从而将踏面缺陷类型进行分类,并将分类结果用可视化数据显示。实验结果表明,采用上述所提方法,对车轮踏面缺陷不同类型的分类识别精度达96%以上。Wheels are one of the key components of the running part of the train.Defects in its tread will directly affect the safety of train operation.In order to accurately identify different types of wheel tread defects during inspection, a texture feature extraction method based on gray-gradient co-occurrence matrix is proposed.After analyzing the gray and gradient features of the tread image, image texture feature vector is extracted according to the gray-gradient co-occurrence matrix.Then combined with the K-means clustering optimization algorithm to cluster the characteristics of tread defects, thereby classifying the types of tread defects, and displaying the classification results with visual data.The experimental results show that the accuracy of classifying and identifying different types of wheel tread defects is over 96% by using the above-mentioned algorithm.

关 键 词：踏面缺陷 灰度-梯度共生矩阵 纹理特征 K-均值(K-means)聚类 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]