Heavy fleet health monitoring
Telemetry from haul trucks and plant used to predict failures at remote sites.
The problem
Breakdowns at remote sites cause long stoppages while parts and engineers travel.
Data we need
- Telematics and engine data
- Oil analysis
- Maintenance history
How it works
- Connect fleet telemetry
- Build health and failure models
- Run on site edge servers
- Plan interventions and parts
- Monitor model accuracy
What it changes
Targets are agreed with you before we build, and measured on your data before release.
- Less unplanned downtime
- Parts on site before failure
- Works without connectivity
Time series and forecasting
Demand, load and failure forecasting from sensors, meters and transaction history.
- Temporal CNNs
- Prophet-style models
- Anomaly detection