AI Case Study

GE achieves speed and accuracy in detecting track flaws in real time with machine learning

General Electric (GE) has equipped its freight locomotives with sensors, such as cameras that capture footage of the track and the cab and feed it to machine learning analytic software which is able to process it in real time and determine whether there is a danger. In this way the company has achieved gains in speed and accuracy of detecting things on or around the track and has improved the efficiency of its rail transport solutions.

Industry

Transportation

Freight And Logistics

Project Overview

"Each of GE’s smart freight locomotives is equipped with sensors including cameras that capture track, front and back, and the cab of the locomotive. The data from the sensors is fed to machine-learned analytic applications which aggregate the data right there on the edge gateway, enabling onboard real-time decision-making." (techemergence)

"EdgeLINC enables complete user control over configuration, telemetry, alerts and leverages SAS’s Event Stream Processing (ESP) engine integrated with Predix Machine, Predix Edge Manager and Asset Performance Management (APM) solutions. EdgeLINC is capable of running on GE Transportation’s GoLINC platform as well as third party devices, and supports on premises, cloud and hybrid cloud deployment and integration." (getransportation)

For instance, much of the on-board video analytics are dedicated to the same things that automated car sensors are — instead of the road, they’re inspecting the track, identifying signs and mile posts, and scanning for obstacles on the track. But the biggest impact, Mukai says, is the ability to identify sun kinks, or track deformations, that lead to derailment. Video physically captures track flaws; machine-learned models can detect whether they’re a danger to the locomotive." (Venturebeat)

Reported Results

"We’re seeing great gains there in terms of speed, because accuracy detecting things on track or things around the track is up to 99 percent because of AI." (Venturebeat)
In addition, during the pilot project with Deutsche Bahn in Germany, a 25% reduction in locomotive failure rates was recorded. Although, it is not clear what the baseline readings for these metrics were, thus a concrete measurable impact may not be feasible at the time of writing. (techemergence)

Technology

"The data from the sensors is fed to machine-learned analytic applications which aggregate the data right there on the edge gateway, enabling onboard real-time decision-making." (techemergence)

Function

Operations

Field Services

Background

"Industrial assets generate valuable information at the edge – or on a machine or device – where embedded sensors collect vast amounts of data. When operating heavy machinery in variable environments, the ability to compute, manage, analyze and act upon that data is essential for companies to benefit from the Industrial Internet. In the rail industry, assets are mobile and constantly moving in and out of communication, making it even harder to derive value from data that lives on the edge." (getransportation)

Benefits

Data

""Each of GE’s smart freight locomotives is equipped with sensors including cameras that capture track, front and back, and the cab of the locomotive." (techemergence)