a4805947d1
feat: Add NX study models and optimization histories
...
Includes all study folders with NX models for development:
- bracket_stiffness_optimization (V1, V2, V3)
- drone_gimbal_arm_optimization
- simple_beam_optimization
- uav_arm_optimization (V1, V2)
- training_data_export_test
- uav_arm_atomizerfield_test
Contains .prt, .fem, .sim files and optimization databases.
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2025-11-26 12:19:07 -05:00
d228ccec66
refactor: Archive experimental LLM features for MVP stability (Phase 1.1)
...
Moved experimental LLM integration code to optimization_engine/future/:
- llm_optimization_runner.py - Runtime LLM API runner
- llm_workflow_analyzer.py - Workflow analysis
- inline_code_generator.py - Auto-generate calculations
- hook_generator.py - Auto-generate hooks
- report_generator.py - LLM report generation
- extractor_orchestrator.py - Extractor orchestration
Added comprehensive optimization_engine/future/README.md explaining:
- MVP LLM strategy (Claude Code skills, not runtime LLM)
- Why files were archived
- When to revisit post-MVP
- Production architecture reference
Production runner confirmed: optimization_engine/runner.py is sole active runner.
This establishes clear separation between:
- Production code (stable, no runtime LLM dependencies)
- Experimental code (archived for post-MVP exploration)
Part of Phase 1: Core Stabilization & Organization for MVP
Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com >
2025-11-24 09:12:36 -05:00
15c06f7b6c
fix: Stop passing design_vars to simulation_runner to match working 50-trial workflow
...
**CRITICAL FIX**: FEM results were identical across trials
**Root Cause**:
The LLM runner was passing design_vars to simulation_runner(), which then passed
them to NX Solver's expression_updates parameter. The solve journal tried to
update hardcoded expression names (tip_thickness, support_angle) that don't exist
in the beam model, causing the solver to ignore updates and use cached geometry.
**Solution**:
Match the working 50-trial optimization workflow:
1. model_updater() updates PRT file via NX import journal
2. Part file is closed/flushed to disk
3. simulation_runner() runs WITHOUT passing design_vars
4. NX solver loads SIM file, which references the updated PRT from disk
5. FEM regenerates with updated geometry automatically
**Changes**:
- llm_optimization_runner.py: Call simulation_runner() without arguments
- run_optimization.py: Remove design_vars parameter from simulation_runner closure
- import_expressions.py: Added theSession.Parts.CloseAll() to flush changes
- test_phase_3_2_e2e.py: Fixed remaining variable name bugs
**Test Results**:
✅ Trial 0: objective 7,315,679
✅ Trial 1: objective 9,158.67
✅ Trial 2: objective 7,655.28
FEM results are now DIFFERENT for each trial - optimization working correctly!
**Remaining Issue**: LLM parsing "20 to 30 mm" as 0-1 range (separate fix needed)
2025-11-17 21:29:21 -05:00
b4c0831230
fix: Remove redundant save() call that overwrote NX expression updates
...
Critical bug fix for LLM mode optimization:
**Problem**:
- NXParameterUpdater.update_expressions() uses NX journal to import expressions (default use_nx_import=True)
- The NX journal directly updates the PRT file on disk and saves it
- But then run_optimization.py was calling updater.save() afterwards
- save() writes self.content (loaded at initialization) back to file
- This overwrote the NX journal changes with stale binary content!
**Result**: All optimization trials produced identical FEM results because the model was never actually updated.
**Fixes**:
1. Removed updater.save() call from model_updater closure in run_optimization.py
2. Added theSession.Parts.CloseAll() in import_expressions.py to ensure changes are flushed and file is released
3. Fixed test_phase_3_2_e2e.py variable name (best_trial_file → results_file)
**Testing**: Verified expressions persist to disk correctly with standalone test.
Next step: Address remaining issue where FEM results are still identical (likely solve journal not reloading updated PRT).
2025-11-17 21:24:02 -05:00
fe2ef9be6d
feat: Implement Study Organization System (Organization v2.0)
...
Reorganized simple_beam_optimization study and created templates for future
studies following best practices for clarity, chronology, and self-documentation.
## Study Reorganization (simple_beam_optimization)
**New Directory Structure**:
```
studies/simple_beam_optimization/
├── 1_setup/ # Pre-optimization setup
│ ├── model/ # Reference CAD/FEM model
│ └── benchmarking/ # Baseline validation results
├── 2_substudies/ # Optimization runs (numbered chronologically)
│ ├── 01_initial_exploration/
│ ├── 02_validation_3d_3trials/
│ ├── 03_validation_4d_3trials/
│ └── 04_full_optimization_50trials/
└── 3_reports/ # Study-level analysis
└── COMPREHENSIVE_BENCHMARK_RESULTS.md
```
**Key Changes**:
1. **Numbered Substudies**: 01_, 02_, 03_, 04_ indicate chronological order
2. **Reorganized Setup**: model/ and benchmarking/ moved to 1_setup/
3. **Centralized Reports**: Study-level docs moved to 3_reports/
4. **Substudy Documentation**: Each substudy has README.md explaining purpose/results
## Updated Metadata
**study_metadata.json** (v2.0):
- Tracks all 4 substudies with creation date, status, purpose
- Includes result summaries (best objective, feasible count)
- Documents new organization version
**Substudies Documented**:
- 01_initial_exploration - Initial design space exploration
- 02_validation_3d_3trials - Validate 3D parameter updates
- 03_validation_4d_3trials - Validate 4D updates including hole_count
- 04_full_optimization_50trials - Full 50-trial optimization
## Templates for Future Studies
**templates/study_template/** - Complete study structure:
- README.md template with study overview format
- study_metadata.json template with v2.0 schema
- Pre-created 1_setup/, 2_substudies/, 3_reports/ directories
**templates/substudy_README_template.md** - Standardized substudy documentation:
- Purpose and hypothesis
- Configuration changes from previous run
- Expected vs actual results
- Validation checklist
- Lessons learned
- Next steps
**templates/HOW_TO_CREATE_A_STUDY.md** - Complete guide:
- Quick start (9 steps from template to first run)
- Substudy workflow
- Directory structure reference
- Naming conventions
- Best practices
- Troubleshooting guide
- Examples
## Benefits
**Clarity**:
- Numbered substudies show chronological progression (01 → 02 → 03 → 04)
- Clear separation: setup vs. optimization runs vs. analysis
- Self-documenting via substudy READMEs
**Discoverability**:
- study_metadata.json provides complete substudy registry
- Each substudy README explains what was tested and why
- Easy to find results for specific runs
**Scalability**:
- Works for small studies (3 substudies) or large studies (50+)
- Chronological numbering scales to 99 substudies
- Template system makes new studies quick to set up
**Reproducibility**:
- Each substudy documents configuration changes
- Purpose and results clearly stated
- Lessons learned captured for future reference
## Implementation Details
**reorganize_study.py** - Migration script:
- Handles locked files gracefully
- Moves files to new structure
- Provides clear progress reporting
- Safe to run multiple times
**Organization Version**: 2.0
- Tracked in study_metadata.json
- Future studies will use this structure by default
- Existing studies can migrate or keep current structure
## Files Added
- templates/study_template/ - Complete study template
- templates/substudy_README_template.md - Substudy documentation template
- templates/HOW_TO_CREATE_A_STUDY.md - Comprehensive creation guide
- reorganize_study.py - Migration script for existing studies
## Files Reorganized (simple_beam_optimization)
**Moved to 1_setup/**:
- model/ → 1_setup/model/ (CAD/FEM reference files)
- substudies/benchmarking/ → 1_setup/benchmarking/
- baseline_validation.json → 1_setup/
**Renamed and Moved to 2_substudies/**:
- substudies/initial_exploration/ → 2_substudies/01_initial_exploration/
- substudies/validation_3trials/ → 2_substudies/02_validation_3d_3trials/
- substudies/validation_4d_3trials/ → 2_substudies/03_validation_4d_3trials/
- substudies/full_optimization_50trials/ → 2_substudies/04_full_optimization_50trials/
**Moved to 3_reports/**:
- COMPREHENSIVE_BENCHMARK_RESULTS.md → 3_reports/
**Substudy-Specific Docs** (moved to substudy directories):
- OPTIMIZATION_RESULTS_50TRIALS.md → 2_substudies/04_full_optimization_50trials/OPTIMIZATION_RESULTS.md
## Documentation Created
Each substudy now has README.md documenting:
- **01_initial_exploration**: Initial exploration purpose
- **02_validation_3d_3trials**: 3D parameter update validation
- **03_validation_4d_3trials**: hole_count validation success
- **04_full_optimization_50trials**: Full results, no feasible designs found
## Next Steps
**For Future Studies**:
1. Copy templates/study_template/
2. Follow templates/HOW_TO_CREATE_A_STUDY.md
3. Use numbered substudies (01_, 02_, ...)
4. Document each substudy with README.md
**For Existing Studies**:
- Can migrate using reorganize_study.py
- Or apply organization v2.0 to new substudies only
- See docs/STUDY_ORGANIZATION.md for migration guide
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2025-11-17 19:20:45 -05:00
