|
The maintenance of trains, especially those that are a few miles long, demands substantial time for inspection. The conventional way is to walk around each train car and examine the train for damages. This takes too long, demands resources and a high level of expertise to detect defects, and results in downtime, rendering the train out of service during the inspection.
To overcome this challenge, railroad companies are investing in the research and development of intelligent digital inspection portals using AI, machine learning, and machine vision. Railroads such as UP, CN, Norfolk, and Southern are among those companies.
According to the Georgia Tech Research Institute (GTRI), it has developed Digital Inspection Portals (DTI) for Norfolk Southern Corporation that use advanced machine vision and AI to examine trains moving at speeds of up to 70 miles per hour to identify mechanical defects that may exist (Figure 7???).
Machine vision technology in the portals produces images of key components located on the front and back, top, bottom, and sides of train cars, providing a 360° view of the complete train. Images produced by the portal are analyzed within minutes of a train’s passage, allowing issues to be identified and reported immediately.
Full Article: IEEE Vehicular Technology Magazine, Volume 20, Number 3, September 2025
|
