Antoine/Atomizer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
3d90097b2b1cc5cd425b57c7005936717759561a
Atomizer/optimization_engine
History
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
..
custom_functions
feat: Complete Phase 2.5-2.7 - Intelligent LLM-Powered Workflow Analysis
2025-11-16 13:35:41 -05:00
extractors
feat: Add Phase 2 & 3 physics extractors for multi-physics optimization
2025-12-06 13:40:14 -05:00
future
refactor: Archive experimental LLM features for MVP stability (Phase 1.1)
2025-11-24 09:12:36 -05:00
gnn
feat: Add Zernike GNN surrogate module and M1 mirror V12/V13 studies
2025-12-10 08:44:04 -05:00
hooks
feat: Add MLP surrogate with Turbo Mode for 100x faster optimization
2025-12-06 20:01:59 -05:00
plugins
feat: Add substudy system with live history tracking and workflow fixes
2025-11-16 21:29:54 -05:00
result_extractors
fix: Remove redundant save() call that overwrote NX expression updates
2025-11-17 21:24:02 -05:00
schemas
feat: Add configuration validation system for MVP stability (Phase 1.2)
2025-11-24 09:21:55 -05:00
templates
feat: Implement Agentic Architecture for robust session workflows
2025-12-07 14:52:25 -05:00
utils
feat: Add Protocol 13 adaptive optimization, Plotly charts, and dashboard improvements
2025-12-04 07:41:54 -05:00
validators
feat: Add Protocol 13 adaptive optimization, Plotly charts, and dashboard improvements
2025-12-04 07:41:54 -05:00
__init__.py
Rebrand project from nx-optimaster to Atomizer
2025-11-15 08:05:19 -05:00
active_learning_surrogate.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
adaptive_characterization.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
adaptive_surrogate.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
auto_doc.py
feat: Implement Agentic Architecture for robust session workflows
2025-12-07 14:52:25 -05:00
auto_trainer.py
feat: Add neural loop automation - templates, auto-trainer, CLI
2025-11-26 07:53:00 -05:00
base_runner.py
feat: Implement Agentic Architecture for robust session workflows
2025-12-07 14:52:25 -05:00
benchmarking_substudy.py
feat: Add centralized configuration system and Phase 3.2 enhancements
2025-11-17 14:36:00 -05:00
capability_matcher.py
feat: Complete Phase 2.5-2.7 - Intelligent LLM-Powered Workflow Analysis
2025-11-16 13:35:41 -05:00
codebase_analyzer.py
feat: Complete Phase 2.5-2.7 - Intelligent LLM-Powered Workflow Analysis
2025-11-16 13:35:41 -05:00
comprehensive_results_analyzer.py
feat: Add centralized configuration system and Phase 3.2 enhancements
2025-11-17 14:36:00 -05:00
config_manager.py
feat: Add configuration validation system for MVP stability (Phase 1.2)
2025-11-24 09:21:55 -05:00
export_expressions.py
feat: Add robust NX expression import system for all expression types
2025-11-17 12:34:06 -05:00
extractor_library.py
refactor: Implement centralized extractor library to eliminate code duplication
2025-11-18 09:00:10 -05:00
feature_registry.json
feat: Complete Phase 2.5-2.7 - Intelligent LLM-Powered Workflow Analysis
2025-11-16 13:35:41 -05:00
generate_history_from_trials.py
feat: Complete Phase 3.3 - Visualization & Model Cleanup System
2025-11-17 19:07:41 -05:00
generate_report_markdown.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
generate_report.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
generic_surrogate.py
feat: Implement Agentic Architecture for robust session workflows
2025-12-07 14:52:25 -05:00
hybrid_study_creator.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
import_expressions.py
fix: Remove redundant save() call that overwrote NX expression updates
2025-11-17 21:24:02 -05:00
intelligent_optimizer.py
feat: Implement Protocol 13 - Real-Time Dashboard Tracking
2025-11-21 15:58:00 -05:00
intelligent_setup.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
landscape_analyzer.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
logger.py
feat: Add structured logging system for production-ready error handling (Phase 1.3)
2025-11-24 09:27:27 -05:00
mesh_converter.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
method_selector.py
docs: Update protocol docs and method selector improvements
2025-12-07 19:10:45 -05:00
model_cleanup.py
feat: Complete Phase 3.3 - Visualization & Model Cleanup System
2025-11-17 19:07:41 -05:00
neural_surrogate.py
feat: Add Protocol 13 adaptive optimization, Plotly charts, and dashboard improvements
2025-12-04 07:41:54 -05:00
nx_session_manager.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
nx_solver.py
feat: Add Protocol 13 adaptive optimization, Plotly charts, and dashboard improvements
2025-12-04 07:41:54 -05:00
nx_updater.py
refactor: Centralize NX and environment configuration in config.py
2025-11-17 14:31:33 -05:00
op2_extractor.py
fix: Remove arbitrary aspect ratio validation and add comprehensive pruning diagnostics
2025-11-20 20:25:33 -05:00
optimization_config_builder.py
feat: Add optimization configuration builder with multi-objective support
2025-11-15 13:56:41 +00:00
optimization_setup_wizard.py
feat: Add substudy system with live history tracking and workflow fixes
2025-11-16 21:29:54 -05:00
pruning_logger.py
fix: Remove arbitrary aspect ratio validation and add comprehensive pruning diagnostics
2025-11-20 20:25:33 -05:00
pynastran_research_agent.py
feat: Add substudy system with live history tracking and workflow fixes
2025-11-16 21:29:54 -05:00
realtime_tracking.py
refactor: Archive experimental LLM features for MVP stability (Phase 1.1)
2025-11-24 09:12:36 -05:00
research_agent.py
feat: Complete Phase 2.5-2.7 - Intelligent LLM-Powered Workflow Analysis
2025-11-16 13:35:41 -05:00
run_optimization.py
fix: Stop passing design_vars to simulation_runner to match working 50-trial workflow
2025-11-17 21:29:21 -05:00
runner_with_neural.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
runner.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
simple_mlp_surrogate.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
simulation_validator.py
fix: Remove arbitrary aspect ratio validation and add comprehensive pruning diagnostics
2025-11-20 20:25:33 -05:00
solve_simulation_simple.py
feat: Add centralized configuration system and Phase 3.2 enhancements
2025-11-17 14:36:00 -05:00
solve_simulation.py
feat: Add MLP surrogate with Turbo Mode for 100x faster optimization
2025-12-06 20:01:59 -05:00
step_classifier.py
feat: Complete Phase 2.5-2.7 - Intelligent LLM-Powered Workflow Analysis
2025-11-16 13:35:41 -05:00
strategy_portfolio.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
strategy_selector.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
study_continuation.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
study_creator.py
feat: Add centralized configuration system and Phase 3.2 enhancements
2025-11-17 14:36:00 -05:00
study_reset.py
feat: Add neural loop automation - templates, auto-trainer, CLI
2025-11-26 07:53:00 -05:00
study_state.py
feat: Implement Agentic Architecture for robust session workflows
2025-12-07 14:52:25 -05:00
study_wizard.py
feat: Add MLP surrogate with Turbo Mode for 100x faster optimization
2025-12-06 20:01:59 -05:00
surrogate_tuner.py
feat: Improve dashboard performance and Claude terminal context
2025-12-04 17:36:00 -05:00
targeted_research_planner.py
feat: Complete Phase 2.5-2.7 - Intelligent LLM-Powered Workflow Analysis
2025-11-16 13:35:41 -05:00
template_loader.py
feat: Add neural loop automation - templates, auto-trainer, CLI
2025-11-26 07:53:00 -05:00
training_data_exporter.py
feat: Major update with validators, skills, dashboard, and docs reorganization
2025-11-25 19:23:58 -05:00
visualizer.py
feat: Complete Phase 3.3 - Visualization & Model Cleanup System
2025-11-17 19:07:41 -05:00
workflow_decomposer.py
feat: Complete Phase 2.5-2.7 - Intelligent LLM-Powered Workflow Analysis
2025-11-16 13:35:41 -05:00