본문으로 건너뛰기
D.Hub
KOEN
Manufacturing
95 min

Choose a CNC inspection order from four HIGH alerts

Act as a fictional FabriSense maintenance specialist and use sensor quality signals, health scores, and an ontology that reaches technicians, locations, and shifts to order four CNC inspections.

0/7 chapters complete

A maintenance shift with four alerts on the board

The morning shift has started at the fictional CNC manufacturer FabriSense. Two days of readings produced six anomalies, and CNC-03, CNC-05, CNC-07, and CNC-09 are all HIGH. Immediately available maintenance staff is limited, so they need a first stop without discarding the other three warnings.

Today, you are the FabriSense maintenance specialist answering this question:

Which CNC machine should we inspect first to prevent a failure, and what evidence supports that order?

A fictional FabriSense maintenance specialist compares alerts from several CNC machines and selects the first inspection target
Fictional scenario illustration — an AI-generated image of ordering HIGH alerts, not a real product screen.

Decision criteria for this mission

  • Perspectives in play — Maintenance analysis determines whether each alert came from a statistical threshold or an explicit condition signal. Field operations assigns a first stop per technician and decides what can run in parallel.
  • Decision constraints — CNC-03, CNC-05, CNC-07, and CNC-09 are all HIGH, and each has a health score of 90. Choosing a first machine does not justify returning the other three to normal operation.
  • Completion signals — Explain the source of all four alerts, use the published Workshop tie-break rule to place CNC-03 first, and leave the technician, zone, and shift that the next specialist can retrace.

Workshop goals

  • Read sensor values together with quality_flag to identify the source of an alert.
  • Explain in plain language what a three-sigma check finds.
  • Compress six anomaly rows into machine health scores that separate inspection from watch.
  • Connect technician, location, and shift to machine, sensor, and event to fill all five top categories.
  • Separate an operational policy from the workshop's tie-break rule.

Seven decisions

Loading the diagram. Mermaid source:

flowchart LR
    accTitle: Seven decisions for ordering CNC inspections
    accDescr: Start with four alerts, read the sensor evidence and three-sigma rule, set the inspection order, connect technician location and shift, check the core reasoning, and explain the maintenance decision.
    warnings["1. Confirm four alerts"] --> evidence["2. Read sensor evidence"]
    evidence --> sigma["3. Understand 3-sigma"]
    sigma --> order["4. Set inspection order"]
    order --> context["5. Connect who, where, when"]
    context --> check["6. Check understanding"]
    check --> explain["7. Explain the decision"]

Each chapter follows question → reason → action → observation → interpretation → next decision. Instead of memorizing every asset, narrow the evidence needed to choose the first inspection.

Before you begin

  • An engineer or maintenance-analyst account with Editor access or higher
  • Enough download space for a scenario ZIP of about 45 KB
  • About 95 minutes

You do not need a terminal, Python, or a clone of dhub2-examples. If scenario import is new to you, start with Import and tour a complete hands-on scenario.

Learning journey

  1. Start with four HIGH alerts15 minImport the IoT scenario and separate the evidence and master data needed to order four machine inspections.
  2. Read sensor values together with quality signals15 minRead value, unit, and quality signal together across 216 sensor rows to separate four explicit high-risk signals from rows that cannot be used at all.
  3. Understand the three-sigma check intuitively15 minMeasure how far each reading sits from the norm for its sensor type, and see how the statistical rule and the condition signal split the work of assigning severity.
  4. Turn alerts into an inspection order20 minCompress six anomalies into machine health scores and use the operations dashboard to choose a first inspection among four HIGH machines.
  5. Connect technician, location, and shift to the machine context20 minMaterialize the IoT ontology and join technician, location, and shift to machine, sensor, and maintenance event so all five top categories are covered.
  6. Check the core maintenance reasoning5 minBefore explaining the final decision, review what set each severity, the sigma rule, technician and location context, and inspection scope in four questions.
  7. Explain the maintenance decision with evidence5 minReturn to the shift question and explain the inspection scope, the first stop, and what runs in parallel among four HIGH machines.