Bearing fault detection
Inner race, outer race and roller faults with severity grading, classified on the sensor node.
Industry
Rail and mobility
What our sensing partner is proving on freight wagons: bearing condition classified on the vehicle, without batteries or cabling.
The situation
What operators and wagon builders tell us
- Freight wagons with no power, no network and no maintenance staff on board.
- Trackside detectors that see a wagon only when it passes one.
- Battery-powered nodes whose maintenance cost exceeds the fault they prevent.
- Approval paths measured in years, and suppliers who pretend otherwise.
Freight wagons have no power, no network and no maintenance staff on board, which is why condition monitoring has stayed trackside and sparse. Our partner NeuroControls GmbH leads a demonstrator in the EU Chips JU EdgeAI project in which a self-powered sensor node on the bearing housing classifies bearing faults on the node and hands the result to a trackside reader as the wagon passes. The same approach applies to wheelsets, bogies and traction motors. Onboard sensing is the next step after trackside detection, and it is a multi-year path to the approvals a national network requires. We say so rather than imply otherwise.
Showcase. This is a capability our sensing partner is proving in a public project, not a delivered client installation. We say so rather than imply otherwise.
Where we help
What the demonstrator points to
Energy-autonomous sensing
Vibration energy harvesting, no battery, data read out by RFID at the trackside.
Wheel and track interaction
Flats, out-of-roundness and rail defects from vibration and airborne acoustics.
Depot and yard surveillance
Acoustic monitoring of shunting, braking and unusual events.
EvidenceFreight-rail bearing demonstrator led by NeuroControls GmbH in the EdgeAI project (Chips JU, grant 101097300), described publicly at edge-ai-tech.eu (25 May 2026).
By asset
The machines we listen to in this sector
Bearings and gearboxes
Wear, lubrication loss and race defects from vibration and airborne acoustics; on-node classification for fleets.
How we would start
The services this sector uses most
Almost every engagement begins with a feasibility study or a discovery call, because the cheapest thing to establish first is whether the signature is there at all.
Energy-efficient edge deploymentModels sized for the hardware and the power budget.Open service page Multi-modal sensing + edge AIRuggedised sensor units and on-device AI.Open service page Co-development R&D and PoCApplied R&D on your process, with your engineers.Open service page Expert consultation & advisorySenior engineering time, by the day or on retainer.Open service page
Start here
Ask about the demonstrator
Tell us the asset or the station, what goes wrong and how often. We answer every enquiry within 48 hours on working days.
- Your data stays on site; on-premise and on-device deployment is the default
- We work alongside the monitoring system you already run
- Honest go / no-go before any large spend
Ready to find out if it works on your machines?
Start with a free 30 to 45 minute discovery call. Bring the problem, the recordings you already have and your questions. We will tell you honestly whether sensing-based AI is the right tool and what the next step would cost in days, not months.