Antoine/Atomizer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
258 Commits 3 Branches 1 Tag
bb83bb9cab7156e48f7dffd5cc9f501f62450290
Commit Graph

7 Commits

Author SHA1 Message Date
Antoine
d6a1d6eee1 auto: daily sync 2026-02-15 08:00:21 +00:00
Antoine
93a5508c07 Fix mass extraction + db close order + nan handling 
- Journal now extracts p173 mass expression and writes _temp_mass.txt
- history.get_study_summary() called before history.close()
- Optuna nan rejection: fallback to INFEASIBLE_MASS penalty
- pyNastran warning 'nx 2512 not supported' is harmless (reads fine)
 2026-02-11 16:29:45 +00:00
Antoine
815db0fb8d Add persistent trial history DB (append-only, survives --clean) 
- history.db: SQLite append-only, never deleted by --clean
- history.csv: Auto-exported after each trial (live updates)
- Logs: DVs, results, feasibility, status, solve time, iter path
- Cross-study queries: full lineage across all runs/phases
- --clean only resets Optuna DB, history preserved
 2026-02-11 14:59:52 +00:00
Antoine
0e459028fe Fix: FEM part lookup (exclude _i.prt), hole_count unit (Constant not mm), add file logging 
- solve_simulation.py: FEM finder now excludes idealized parts, falls back to loading .fem
- solve_simulation.py: hole_count written as [Constant] not [MilliMeter] in .exp
- run_doe.py: dual logging to console + results/doe_run.log
 2026-02-11 14:17:43 +00:00
Antoine
126f0bb2e0 Refactor: nx_interface uses optimization_engine (NXSolver + pyNastran extractors) 
- AtomizerNXSolver wraps existing NXSolver + extractors from SAT3 pipeline
- HEEDS-style iteration folders with fresh model copies per trial
- Expression .exp file generation with correct unit mapping
- pyNastran OP2 extraction: displacement, von Mises (kPa→MPa), mass
- StubSolver improved with beam-theory approximations
- Reuses proven journal pipeline (solve_simulation.py)
 2026-02-11 13:33:09 +00:00
Antoine
135698d96a Fix: SQLite duplicate study (load_if_exists), sampling crash with n<11, add --clean flag 2026-02-11 13:09:30 +00:00
Antoine
017b90f11e feat(hydrotech-beam): Phase 1 LHS DoE study code 
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
 2026-02-10 22:15:06 +00:00