Railway Track & Structures - February 2009 - (Page 24)

Detect rail defects cracks, which are about 0.25 inches in length,” said Berry. “These cracks are virtually invisible when performing traditional hi-rail inspections. This capability has made a signiﬁcant impact in the early detection of defective bars before they reach 100 percent breaks.” ENSCO has also worked to decrease its false detection rates for both cracks and joint bars and notes that it has made signiﬁcant gains in its productivity on non-uniform rail conditions, such as water-streaked rail or rail that is cluttered with debris. According to ENSCO, the Joint Bar Inspection System has been well received since the railroads started using it in production service in 2006. Five of the Class 1 railroads use this technology to augment their joint inspection processes. The system has been used to “clean up” sections of track that may have had high rates of defective joint bars for an extended period of time, as well as used quarterly to ensure new cracks in bars are identiﬁed and removed immediately. ENSCO points out that, due to demand from the railroads, it has expanded its joint bar ﬂeet to three service trucks. “Many steps have been taken to address any recurring challenges,” said Berry. “For one, data from the ﬁeld are often used to retrain our algorithms to improve detection capabilities in nonuniform rail conditions. We have also added new features and capabilities to the software to help it better identify real cracks often times obscured in the image by debris or ballast.” Herzog Services Inc. has implemented the newest V-30 or “Stingray” technology across its ﬂeet after extensive testing, of which the company called the results “spectacular.” As the two prototype vehicles traveled over their territories, track supervisors, as well as ﬁeld personnel, culled out detected defects that were shelled or had surface irregularities such as head checks or ﬂaking that would have possibly prevented detection using previous technology. These were brought back to Herzog’s facility, cracks and voids. Machine vision-based systems are a good platform for supplementing interior defect inspection with surface defect inspection,” said Andrea Berry, program manager at ENSCO, Inc. In partnership with the Federal Railroad Administration’s Ofﬁce of Research and Development, ENSCO developed the Joint Bar Inspection System, an automated machine vision technology for inspecting surface condition of rail joint bars. The Joint Bar Inspection System can be installed on a hi-rail or track inspection car where it is capable of capturing high-resolution images of the joint bars at up to 65 mph and perform automated processing on the bar images to detect cracks. As a secondary output, the Joint Bar Inspection System provides a GPS inventory of rail joints. ENSCO added a few signiﬁcant features to the Joint Bar Inspection System based on customer feedback in the past year, including reﬁning the detection of very small cracks. “We developed algorithms to ﬁnd what the industry calls ‘ﬁve percent’ Herzog 24 Railway Track & Structures February 2009 www.rtands.com http://www.airtecinternational.com http://www.dixieprecast.com/ http://www.dixieprecast.com/ http://www.rtands.com

Table of Contents Feed for the Digital Edition of Railway Track & Structures - February 2009

Railway Track and Structures - February 2009 Contents On Track Industry Today Supplier News AREMA News NRC News TTCI R&D Railroads Stepping Up Use of Technology to Locate Rail Flaws Rail Lubrication Realizing Great Potential M/W Challenges: Track Settlement at Bridge Approaches Supplier Profiles Products and Literature People Calendar Advertisers Index Sales Representatives Website Directory Professional Directory Classified Advertising Chicago Perspective

Railway Track & Structures - February 2009

For optimal viewing of this digital publication, please enable JavaScript and then refresh the page. If you would like to try to load the digital publication without using Flash Player detection, please click here.