Twincat Export Preparation

Workflow

1. Identify the candidate model or workflow being evaluated for TwinCAT-facing preparation.
2. Separate: reference-backed deployment facts, current repository implementation, and open inference.
3. Check whether the proposed path preserves: explicit operating variables, inspectable intermediate quantities, and analytical-versus-ML separation.
4. Prefer harmonic quantities, conditioned coefficients, or other explicit decomposition outputs over opaque end-to-end inference stories.
5. State clearly whether the result is: deployment-plausible, export-preparable, or actually deployment-ready.

Repository Priorities

• Treat rotational transmission error as the target signal.
• Keep speed, torque, oil temperature, angle, encoder zeroing, and DataValid semantics explicit when they matter.
• Prefer structured or hybrid models with inspectable components over opaque black-box deployment stories.
• Keep TwinCAT/PLC claims grounded in repository code, reference notes, or clearly labeled inference.

Output Pattern

Prefer this structure:

1. What the reference and current repository actually support.
2. What makes the candidate export-plausible or not.
3. What export/simplification steps are still required.
4. What remains speculative or unimplemented.

File Targets To Read First

• doc/reference_codes/testrig_twincat_ml_reference.md
• doc/reference_summaries/
• doc/technical/2026-03/2026-03-26/2026-03-26-15-43-43_twincat_ml_export_and_testrig_reference_analysis.md
• relevant doc/guide/
• relevant scripts/models/
• relevant scripts/training/

Typical Outputs

• TwinCAT export-preparation note;
• PLC-friendly feasibility review;
• required simplification/export checklist;
• deployment-readiness boundary statement.