FINNISH rolling stock maintenance company VR FleetCare will deploy Train Scanner, a device designed to automatically inspect the external condition of trains, in June and use it for the maintenance of trains operating in the Helsinki area. The objective is to be able to reliably identify any malfunctions and blemishes on train exteriors.
Train Scanner has been developed in cooperation with Vire Labs, a Finnish company providing IoT solutions based on machine intelligence.
Train Scanner uses machine vision, shape recognition and artificial intelligence (AI). Poles which are 6.5m high and fitted with scanners are installed on both sides of the track and used to scan passing trains. The sides and roof of the train are scanned using a line camera with extremely high imaging speed and analysis accuracy with a resolution of a few millimetres. The data from the scanner is processed immediately using edge computing which analyses the data and reports any deviations to train maintenance staff. The data is also stored in the cloud to enable further analysis.
“The shutter speed and resolution of the camera could be compared with photo-finish cameras used in sports competitions,” says Mr Samuli Suuriniemi, VR FleetCare’s Train Scanner project manager. “We taught the device what a train should look like so that it can automatically detect any deviations. AI becomes increasingly more accurate based on the feedback the device receives from humans. The final objective is to be able to detect any rolling stock malfunctions in a reliable manner.”
VR FleetCare says Train Scanner has been piloted for one year with excellent results, and in June, will be deployed by the first rolling stock owner. Stadler Flirt commuter trains operating in the Helsinki will be inspected using Train Scanner by driving the trains past the device before arriving at the depot.
“There are various benefits related to implementing the system,” says Suuriniemi. “The condition of rolling stock is constantly assessed, and safety is improved as the system can detect malfunctioning components of a bogie, for example. By utilising the data available, it will also be possible to accurately define maintenance intervals in the future. Inspection intervals can also be easily increased.
So far, Train Scanner has only been tested with passenger trains but, due to its scalability, the device can be used to inspect any rolling stock. Train Scanner could be used at border stations to automatically detect whether the size of a wagon adheres to the local instructions or verify wagon safety.
Train Scanner is not completely new, as a few devices with similar user purposes already exist. “The prices of the devices available are quite high, and their installation requires extensive construction work,” says Mr Mihail Lipiäinen, VR FleetCare’s vice-president, digital services. “Our intention has been to develop a cost-effective solution that is scalable and possible to implement quickly. Automated inspection of rolling stock will be one of the most important changes made possible by the current technology, and the benefits for the owner of the rolling stock include improved maintenance quality and better rolling stock usability.”