Railway trains and tracks are complex assets that require constant inspection, management and maintenance. Cogniac helps to reduce the likelihood of derailments, the cost and disturbance of which can be catastrophic for an organization.
The freight railway is one of the oldest transport infrastructures in North America but is busier now than it has ever been. More trains are pulling more cars on a daily basis than ever before to deliver goods around the country.
Human subject matter experts are expected to monitor and inspect tens of thousands of wheels every day on an average size railroad, in addition to tens of thousands of miles of track. Even using traditional machine vision, operators would have to spend hours evaluating images and often the software wouldn’t pick up an error due to the variability in the defect.
Cogniac’s solution allows railway companies to evaluate, in near real time, train wheels and tracks at speeds of up to 60mph. From wheel cracks, rail splits, and missing bolts, Cogniac delivers its incredibly powerful AI solution where the rail companies need it most – on the line itself.
Cogniac deploys its AI machine vision platform on the edge to enable railway companies to process the images they capture on-location and within a minute, providing near instant evaluation of critical assets on the move.
Case Study – Freight Railroad
Cogniac is working with one of the largest freight railroads in North America and, on a monthly basis, monitors 22 million wheels and 32,500 miles of track. The solution deployed for the railway operator enables them to evaluate these hugely important assets in real-time and at speeds of up to 60mph.
AI at the Edge
Cogniac processes hundreds of thousands of images taken by cameras on the front of over 450 trains each month. As the train is moving, the images are sent to the edge by Cogniac’s EdgeFlow and evaluated for any splits, cracks or missing bolts. Within a minute a human subject matter expert is alerted if any images are flagged as defective. The human supervisor can then make a decision on how to proceed with the defect identified.
Additionally, Cogniac has worked with the railway operator to install trackside gantries that take high resolution images of the wheels as they pass at 60mph. The images are processed and cracks or other issues are sent to a human inspector for secondary review.
Cogniac’s AI uses Hyper Parameter Optimization to enable it to identify any shape of crack or defect on these valuable assets. Since January 2020 Cogniac’s vision system has stopped over 100 trains where there was a potentially devastating issue that could lead to a derailment, saving the railway up to $350m in damages.