Antoine
017b90f11e
Implements the optimization study code for Phase 1 (LHS DoE) of the Hydrotech Beam structural optimization. Files added: - run_doe.py: Main entry point — Optuna study with SQLite persistence, Deb's feasibility rules, CSV/JSON export, Phase 1→2 gate check - sampling.py: 50-point LHS via scipy.stats.qmc with stratified integer sampling ensuring all 11 hole_count levels (5-15) are covered - geometric_checks.py: Pre-flight feasibility filter — hole overlap (corrected formula: span/(n-1) - d ≥ 30mm) and web clearance checks - nx_interface.py: NX automation module with stub solver for development and NXOpen template for Windows/dalidou integration - requirements.txt: optuna, scipy, numpy, pandas Key design decisions: - Baseline enqueued as Trial 0 (LAC lesson) - All 4 DV expression names from binary introspection (exact spelling) - Pre-flight geometric filter saves compute and prevents NX crashes - No surrogates (LAC lesson: direct FEA via TPE beats surrogate+L-BFGS) - SQLite persistence enables resume after interruption Tested end-to-end with stub solver: 51 trials, 12 geometric rejects, 39 solved, correct CSV/JSON output. Ref: OPTIMIZATION_STRATEGY.md, auditor review 2026-02-10
Hydrotech Beam — Structural Optimization
Client: Hydrotech (internal test fixture) Channel: #project-hydrotech-beam Created: 2026-02-08 Status: Technical Breakdown Complete — Awaiting Gap Resolution
Objective
Optimize a sandwich I-beam with lightening holes: minimize mass while meeting stiffness and strength constraints.
Key Numbers
| Metric | Baseline | Target |
|---|---|---|
| Mass | ~974 kg | Minimize |
| Tip displacement | ~22 mm | ≤ 10 mm |
| Von Mises stress | TBD | ≤ 130 MPa |
Design Variables
| Variable | Range | Type |
|---|---|---|
| Half-core thickness | 10–40 mm | Continuous |
| Face thickness | 10–40 mm | Continuous |
| Hole diameter | 150–450 mm | Continuous |
| Hole count | 5–15 | Integer |
Approach
Two-phase optimization:
- DoE (LHS, 40–50 trials) — map the landscape
- TPE (Bayesian, 60–100 trials) — converge to optimum
Total budget: ~100–150 NX evaluations, est. 2–5 hours compute.
Project Structure
hydrotech-beam/
├── README.md ← You are here
├── CONTEXT.md # Intake requirements
├── BREAKDOWN.md # Technical analysis
├── DECISIONS.md # Decision log
├── models/ # Reference NX models (golden copies)
├── kb/ # Living knowledge base
│ ├── components/ # Per-component knowledge
│ ├── materials/ # Material data
│ ├── fea/ # FEA model knowledge
│ └── dev/ # Generation documents
├── images/ # Screenshots, plots, renders
├── studies/ # Optimization campaigns
│ └── 01_doe_landscape/ # (first study — pending)
└── deliverables/ # Final reports and recommendations
Key Documents
- CONTEXT.md — Full intake data
- BREAKDOWN.md — Tech Lead's technical analysis
- DECISIONS.md — All project decisions
- kb/_index.md — Knowledge base overview
Team
| Role | Agent | Status |
|---|---|---|
| Manager | 🎯 Manager | Coordinating |
| Technical Lead | 🔧 Tech Lead | Breakdown complete |
| CEO | Antoine | Gap resolution pending |