Scenario context
An onshore wind plant must coordinate fleet power output, pitch shutdown interlocks, substation protection, and centralized alarms. MagicGrid organizes requirements, behavior, structure, and parameters so plant-level and turbine-level models can evolve in parallel without losing traceability.
Energy scenarios highlight interface complexity: turbine OEM controllers, grid codes, SCADA historians, and maintenance workflows. The industry reference scenario abstracts those layers for teaching and product demo — no real owner, turbine model, or SCADA vendor names appear.
MagicGrid domain split
| Domain | Examples |
|---|---|
| Problem | Grid compliance, availability, personnel and asset safety |
| Solution | Dispatch strategy, interlock logic, alarm severity |
| Implementation | SCADA points, protocol mapping, O&M screens |
Operations viewpoint
Operators think in curtailment orders, storm shutdowns, and fire response. Engineers think in pitch curves, brake paths, and communication timeouts. MagicGrid keeps both languages connected — exactly the kind of cross-link MBSE RAG should retrieve when someone says, this sprint we model the storm shutdown interlock sequence.
AI4MBSE and KB usage
During an interlock sequence session, AI4MBSE pulls peer behavior fragments and parameter limits from the engineering knowledge base, proposes message flows and guard conditions, and waits for confirmation before write-back. This one-diagram-at-a-time rhythm matches how multi-OEM wind teams actually review changes.
SysML tooling notes
Teams may host models in MagicDraw, Cameo, or explore SysML v2 text/API routes for automated checks. The scenario is tool-agnostic: kernel plus adapter, not locked to a single vendor — consistent with Ark product direction and OMG SysML v2 evolution.
Curtailment and grid codes
Grid codes change by region; the reference encodes placeholder parameters for ramp rates and reactive power without naming real utilities. When engineers model dispatch behavior, retrieved fragments remind them which parameters require legal review vs. which are internal tuning — keeping AI suggestions inside governance boundaries.
MBSE RAG value in this scenario
Industry reference scenarios exist so the engineering knowledge base can store reusable slices — requirements phrasing, allowed diagram sequences, naming prefixes, and verification hooks — without exposing any real customer program. When AI4MBSE runs a one-diagram-at-a-time session, MBSE RAG should pull only the fragments that belong to the active methodology and view. That keeps conversational modeling honest: candidates stay checkable, human-in-the-loop write-back stays authoritative, and reviewers still own baselines under configuration management aligned with INCOSE practice and OMG SysML / SysML v2 vocabulary.