Detection
The Prioritised Anomaly Queue
A prioritised anomaly queue is the inverse of a traditional BMS alarm list — every detected issue is scored, classified, and ranked so the operator knows what to act on first, and why.
Traditional BMS alarms are unranked: every threshold breach fires with equal weight. After a few weeks, operators learn to ignore the buzzer, and real faults disappear into the noise. The prioritised queue inverts the model.
Every anomaly is processed through the same pipeline: severity scoring, classification across six methods, causal filtering to suppress symptoms of a common cause, and ranking against the rest of the queue. The result is a single ordered list — twenty items, not two thousand — and each item carries a suggested action.
The queue is the surface most Explore operators spend their day in. Done well, it's the only screen they need.
Related terms
Keep reading
See it in product
FrostLogic Explore
This is the engine that ships sensor intelligence as a product. Anomaly detection across six methods, forecasting with explicit confidence bounds, continuous compliance, and what-if simulation — all grounded in your own telemetry, all explainable, all auditable.
See FrostLogic Explore in action