Digital Twin and Deep Learning Models for the Railway Network
by Dattaraj Rao, Principal Architect, GE Transportation
This talk demonstrates a new approach to track infrastructure monitoring that GE is piloting for customers, using the concept of Digital Twin for network. Using an offline GPU infrastructure, Deep Learning models are created and trained on large volumes of video data to learn the state of healthy track and predict anomalies. A Track Health Index (THI) is calculated by these advanced Deep Learning models for track maintenance planning.
During the talk, real customer use-case videos will be shown, demonstrating analytics on videos from locomotive-mounted cameras with Deep Learning models to calculate and display THI on a map for driving maintenance decisions.