Antoine
|
01a7d7d121
|
docs: Complete M1 mirror optimization campaign V11-V15
## M1 Mirror Campaign Summary
- V11-V15 optimization campaign completed (~1,400 FEA evaluations)
- Best design: V14 Trial #725 with Weighted Sum = 121.72
- V15 NSGA-II confirmed V14 TPE found optimal solution
- Campaign improved from WS=129.33 (V11) to WS=121.72 (V14): -5.9%
## Key Results
- 40° tracking: 5.99 nm (target 4.0 nm)
- 60° tracking: 13.10 nm (target 10.0 nm)
- Manufacturing: 26.28 nm (target 20.0 nm)
- Targets not achievable within current design space
## Documentation Added
- V15 STUDY_REPORT.md: Detailed NSGA-II results analysis
- M1_MIRROR_CAMPAIGN_SUMMARY.md: Full V11-V15 campaign overview
- Updated CLAUDE.md, ATOMIZER_CONTEXT.md with NXSolver patterns
- Updated 01_CHEATSHEET.md with --resume guidance
- Updated OP_01_CREATE_STUDY.md with FEARunner template
## Studies Added
- m1_mirror_adaptive_V13: TPE validation (291 trials)
- m1_mirror_adaptive_V14: TPE intensive (785 trials, BEST)
- m1_mirror_adaptive_V15: NSGA-II exploration (126 new FEA)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
|
2025-12-16 14:55:23 -05:00 |
|
Antoine
|
96b196de58
|
feat: Add Zernike GNN surrogate module and M1 mirror V12/V13 studies
This commit introduces the GNN-based surrogate for Zernike mirror optimization
and the M1 mirror study progression from V12 (GNN validation) to V13 (pure NSGA-II).
## GNN Surrogate Module (optimization_engine/gnn/)
New module for Graph Neural Network surrogate prediction of mirror deformations:
- `polar_graph.py`: PolarMirrorGraph - fixed 3000-node polar grid structure
- `zernike_gnn.py`: ZernikeGNN with design-conditioned message passing
- `differentiable_zernike.py`: GPU-accelerated Zernike fitting and objectives
- `train_zernike_gnn.py`: ZernikeGNNTrainer with multi-task loss
- `gnn_optimizer.py`: ZernikeGNNOptimizer for turbo mode (~900k trials/hour)
- `extract_displacement_field.py`: OP2 to HDF5 field extraction
- `backfill_field_data.py`: Extract fields from existing FEA trials
Key innovation: Design-conditioned convolutions that modulate message passing
based on structural design parameters, enabling accurate field prediction.
## M1 Mirror Studies
### V12: GNN Field Prediction + FEA Validation
- Zernike GNN trained on V10/V11 FEA data (238 samples)
- Turbo mode: 5000 GNN predictions → top candidates → FEA validation
- Calibration workflow for GNN-to-FEA error correction
- Scripts: run_gnn_turbo.py, validate_gnn_best.py, compute_full_calibration.py
### V13: Pure NSGA-II FEA (Ground Truth)
- Seeds 217 FEA trials from V11+V12
- Pure multi-objective NSGA-II without any surrogate
- Establishes ground-truth Pareto front for GNN accuracy evaluation
- Narrowed blank_backface_angle range to [4.0, 5.0]
## Documentation Updates
- SYS_14: Added Zernike GNN section with architecture diagrams
- CLAUDE.md: Added GNN module reference and quick start
- V13 README: Study documentation with seeding strategy
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
|
2025-12-10 08:44:04 -05:00 |
|