Turn alerts into an inspection order
Compress three HIGH alerts into machine health scores and use the operations dashboard to choose a first inspection.
Question for this chapter
When all three machines are HIGH, which one should the crew inspect first?
Why this matters now
Anomaly rows explain events in detail, but the crew needs a machine-level action list. First summarize the alerts, then state the secondary evidence used to break a tie.
Try it
Open the equipment_health_rollup pipeline under processed and select Run. The current calculation
deducts ten points per HIGH alert.
| Machine | HIGH count | Health score | Primary decision |
|---|---|---|---|
| CNC-03 | 1 | 90.0 | Isolate and inspect |
| CNC-05 | 1 | 90.0 | Isolate and inspect |
| CNC-09 | 1 | 90.0 | Isolate and inspect |
Read priority on the dashboard
Open the equipment_health dashboard under processed. With the current seed and pipeline output, its
five widgets mean:
- Machines Online (statistic) — 9 machines with sensor data
- Active Anomalies (statistic) — 3
HIGHanomalies - Health Scores by Machine (bar) — CNC-03, CNC-05, and CNC-09 at 90 each
- Anomalies by Machine (bar) — one anomaly for each of the three machines
- Recent Sensor Readings (table) — up to 100 recent sensor rows
The health scores are tied. Split the decision boundary explicitly:
- Operational safety: isolate and inspect all three machines.
- Workshop tie-break: if one crew needs a starting point, begin with CNC-03 because its vibration reading has the largest relative deviation among the tied alerts (z-score 2.83).
- Remaining order: continue with CNC-09 (1.92), then CNC-05 (1.15).
Next decision
You selected CNC-03 as the first stop, but you still need its connected context. Next, trace the machine, sensors, and maintenance event.