Fleet operations, updates and predictive maintenance
A system is delivered once and maintained for a decade. Most of the cost, and nearly all of the risk, sits in the second part.
One vehicle on a bench is not the problem
Updating one vehicle on a bench is trivial. Updating hundreds in the field — across firmware versions, configurations and hardware revisions accumulated over years, without turning one of them into a brick — is not.
So we build update and configuration systems with the failure cases designed first: updates that either complete or roll back, recovery that works when the write was interrupted, verification that the vehicle is running what the fleet record claims, and staged rollout so a bad release reaches a handful of units instead of all of them.
The mechanism is commercial where commercial is better — Mender over a Yocto image, rather than a bespoke updater nobody outside the building has ever debugged.
Not knowing what is flying is a safety problem
A fleet quietly running different firmware is a fleet whose behaviour cannot be predicted, whose incidents cannot be reproduced, and whose certification basis is a guess. Knowing exactly what every unit is running is a safety property, and we build the tooling that keeps it true.
Components rarely fail without warning
They fail without anyone listening. Motor current signatures drift, cell impedance rises, vibration spectra change, thermal behaviour shifts — usually well before the failure.
We model normal behaviour for each specific airframe and flag departure from it, so maintenance is scheduled against evidence rather than against a calendar or an incident. The aim is a warning with enough flight hours left to act on it, and enough specificity to name the component.
What you get
- Fleet-wide updates with a rollback path and no bricked units
- Certainty about what every unit in the field is running
- Maintenance driven by measured condition, not by calendar or incident
Related work
Tell us the constraint you cannot get past
The mass budget, the latency, the environment, the certification route. We will tell you honestly whether it is something we should be working on — and if it is not, who should.