What you're looking at
The "safe band" for each (asset, parameter). For a given reading we
ask two questions:
- Is the value inside the safe range? (
safe_min ≤ value ≤ safe_max)
- If not, has it crossed into the fail range? (below
fail_min or above fail_max)
The forecasting / anomaly engine uses these bands together with the
model's own prediction to decide whether to raise an event.
How the bands are seeded
For every numeric series the profiler picks the 1st and 99th
percentile from the last 30 days of history and writes them as the
default safe_min / safe_max. That's the
auto source.
An operator can override these in the UI (coming in Phase 5) or
via API. Overrides are tagged manual
and the auto-seeder will never overwrite a manual row.
Columns explained
- Asset / Parameter — which signal the band applies to.
- safe_min / safe_max — normal operating range. Values inside are fine.
- fail_min / fail_max — hard limits. A value below
fail_min or above fail_max means the parameter has failed, regardless of what the model predicted.
- Source — auto (computed by the profiler) or manual (set by an operator).
- Updated by — user ID who last changed it, blank for auto.
- Updated — when the row was last written.
How to use this page
Use it to check what numeric range the service considers normal for a
parameter. If anomalies are firing too eagerly for one signal, the
safe band is probably too tight — widen it via a manual override.
If the band is much wider than reality, real failures could slip
through unflagged.
A row missing fail_min/fail_max simply means
no hard fail limits have been set; only the safe band is in use.