论文部分内容阅读
目前已开发出了钢轨连接板自动视频检测系统,并成功进行了现场裂缝钢轨连接板检测效果评估。联邦铁路管理局研究与开发办公室与ENSCO.INC公司共同为该项研究活动提供资金。该系统利用安装在公路/铁路两用车(图1)上的高分辨率行扫描摄像机和2套钢轨连接板激光传感器进行检测。在两次现场示范检测中,系统对裂缝检测的故障报警率低,达到了预期的要求(检测到的裂缝中40%得到了系统操作人员的确认,60%未被确认)。尽管有15%的裂缝未检测到,但这些裂缝都不是中心裂缝。目前正对检测算法进行修正和试验,以降低裂缝失测率,以及由于道碴过高,植物、油渍、泥土或钢轨连接板附近的其他因素造成的错误判断。
Has developed a rail connecting plate automatic video detection system, and successfully conducted on-site crack rail joint board test results evaluation. The Federal Railroad Administration’s Research and Development Office and ENSCO.INC funded the research activity. The system uses a high-resolution line-scan camera mounted on a road / rail car (Figure 1) and two sets of rail-mounted plate laser sensors. In the two field demonstration tests, the fault alarm rate of the crack detection system was low and the expected requirement was met (40% of the detected cracks were confirmed by the system operator and 60% were not confirmed). Although 15% of the cracks were not detected, none of these cracks were central cracks. Testing algorithms are currently being revised and tested to reduce the rate of fracture failure and misjudgment due to excessive ballast, other factors in the vicinity of plants, grease, soil or rail joints.