模式识别在轮对踏面磨耗检测中的应用  

The Application of Pattern Recognition in the Measurement of Wheel Tread Wear

作　　者：薛琴[1] 陈玮[1] 

机构地区：[1]广东工业大学自动化学院,广州510090

出　　处：《微计算机信息》2007年第22期259-261,共3页Control & Automation

基　　金：广东省教育厅自然科学基金(z03032)

摘　　要：轮对踏面磨耗是危及列车运行安全的主要原因之一,提出了将差影法的模式识别方法应用于火车轮对踏面磨耗检测中。目前我国对火车轮对踏面的检测还停留在手工机械式测量阶段,检测技术落后,人为检测误差大,自动化水平低。将模式识别技术应用于踏面磨耗检测中,方法简单,直观,智能化程度高。本文详细介绍了机器视觉检测原理和差影算法,阐述了将差影法应用于踏面磨耗检测中的具体方法,使踏面磨耗检测进入全面自动化。Wheel tread wear is one of the main causes that threaten safety of trains, a kind of method is put forward, which is the subtraction of pattern recognition applying in the wheel tread wear of trains. Recently, the detecting of the wheel tread stays in phase of handwork and mechanical, the technique is lag, and low automated degree. The application of pattern recognition in the measurement of wheel tread wear, the method is very easy, intuitionist and high intelligent. This letterpress expound principle machine vision and algorithm of subtraction, the embody method of subtraction is expatiated, in order to automation of wheel tread wear detecting.

关 键 词：模式识别 差影 轮对踏面磨耗 机器视觉 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]