基于机器视觉的车辆轮对擦伤在线检测系统研究  

Research on On-line Detection System of Vehicle Wheelset Abrasion Based on Machine Vision

作　　者：孟宪国 黄俐 苏玉东 MENG Xian-guo;HUANG Li;SU Yu-dong(CHN ENERGY Co.,Ltd.,Beijing 100048 China;China Railway Harbin Group of Technology Corp.,Ltd.,Harbin 150006 China;Tianjin Hveic Technologies Co.,Ltd.,Tianjin 301799 China)

机构地区：[1]国能铁路装备有限责任公司,北京100048 [2]哈尔滨国铁科技集团股份有限公司,黑龙江哈尔滨150006 [3]天津哈威克科技有限公司,天津301799

出　　处：《自动化技术与应用》2022年第6期133-137,共5页Techniques of Automation and Applications

摘　　要：机车在长时间运行后,极易出现轮对擦伤、磨损等问题,从而增加机车运行风险。为有效检测轮对擦伤情况,本文利用机器视觉技术设计了车辆轮对擦伤在线检测系统。仿真结果表明:该方法对车辆轮对擦伤位置的定位精准度和采样频率较高,采样时间较短且信息漏检率较低,能够更好地为维护轨道车辆安全运行提供支持。After the locomotive runs for a long time, the problems such as wheel pair abrasion and abrasion are easy to occur, which increases the locomotive running risk. In order to detect wheelset abrasion effectively, an on-line detection system for wheelset abrasion is designed by using machine vision technology. The simulation results show that the proposed method has higher accuracy and sampling frequency, shorter sampling time and lower information missing rate, and can provide better support for maintaining the safe operation of rail vehicles.

关 键 词：机器视觉 轮对擦伤 擦伤检测 中值滤波法 灰度变换 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]