Article Increasing Railroad Maintenance Productivity With the IoT and Azure
By Insight UK / 14 Jun 2019 / Topics: Intelligent edge
-->
By Insight UK / 14 Jun 2019 / Topics: Intelligent edge
Accident prevention is a top priority for railroad companies. The sooner maintenance issues are identified, the faster the repairs to ensure rail safety. Railroad companies are concerned about the safety of workers in the field inspecting or repairing the rail. Minimising on-site inspection time helps protect workers and decreases labour costs.
With approximately 32,000 miles of track, this client required support from thousands of field workers to conduct railroad maintenance inspections. In 2018, the client dedicated $2.4B in capital investments for maintenance projects, which primarily involved replacing and upgrading rail, rail ties and ballasts – and maintaining rolling stock.
The client sought a solution to minimise the time required for personnel to be in the field visually inspecting miles of rail, enabling workers to focus on actual maintenance. The company also wanted real-time alerts to accelerate repairs.
The company believed that a central dashboard for analysing inspection data would allow subject matter experts to identify top priorities, further enhance maintenance productivity, and lower risks for workers and freight travel. Enabling measurable outcomes, such as inspecting high-risk equipment or areas where inspections were particularly critical or cumbersome, was a priority. The client also wanted a simplified way to combine and analyse data for additional process improvements in the future.
To enable monitoring and alerts for rail assets, the client begun investing in connected solutions such as Unmanned Aerial Vehicles (UAVs, known as drones), moving rail cars and intelligent switches. The client was also enhancing its engineering platform to generate real-time data consisting of telemetry: ambient measurements, sensor readings, video and still images.
The UAVs flew up to 400 miles per sortie. When the UAVs returned, the image data was combined with geotagging data and analysed to determine the status of the rail asset. The solution met some primary goals for the railroad company, but a few challenges remained. The data was collected on a USB memory stick after the drone returned to its base, which meant that the data couldn’t be received in real time and the process couldn’t be automated. Furthermore, the collection was done by a third party, leaving the client without direct control of its data — which could end up being decentralised, depending on the drone base and the employee who physically retrieved it.
Second, the drones collected images along the rail line, but the client also wanted the ability to focus on maintenance required on the frogs, or rail switches. Because the railroad company didn’t have the ability to collect the data in real time, it was looking for opportunities to speed the process of data collection and make analysis faster and more efficient.