Atomizer/docs/archive/FEM_REGENERATION_STATUS.md

FEM Regeneration Status

Current Status: EXPRESSIONS NOT LINKED TO GEOMETRY

The optimization loop infrastructure is FULLY FUNCTIONAL, but the stress results are not changing because the parametric model is not properly configured.

✅ Working Components

1. Parameter updates - Expressions in Bracket.prt ARE being updated (verified via binary edit)
2. NX solver - Journal connects to NX GUI and runs solves successfully (~4s per solve)
3. Result extraction - Stress and displacement ARE being read from .op2 files
4. History tracking - All trials ARE being saved to history.json/csv
5. Optimization - Optuna IS exploring the parameter space
6. FEM regeneration workflow - Journal IS executing all required steps:
   • Opens .sim file ✅
   • Switches to Bracket.prt ✅
   • Calls UpdateManager.DoUpdate() to rebuild geometry ✅
   • Switches to Bracket_fem1.fem ✅
   • Calls UpdateFemodel() to regenerate FEM ✅
   • Solves and saves ✅

❌ Root Cause: Expressions Not Linked to Geometry Features

All 3 trials return the SAME stress (197.89159375 MPa) because:

1. Expressions (tip_thickness=20, support_angle=36) exist in Bracket.prt ✅
2. Binary updates correctly modify these expression values ✅
3. Journal calls UpdateManager.DoUpdate() to rebuild geometry ✅
4. BUT: No geometry features reference these expressions ❌
5. Therefore the CAD geometry doesn't change ❌
6. Therefore the FEM doesn't see geometry changes ❌
7. So the mesh stays the same, and stress doesn't change ❌

Evidence

Journal Output (From Test Run)

[JOURNAL] Opening simulation: C:\...\Bracket_sim1.sim
[JOURNAL] Checking for open parts...
[JOURNAL] Opening simulation fresh from disk...
[JOURNAL] STEP 1: Updating Bracket.prt geometry...
[JOURNAL]   Bracket geometry updated (0 errors)  ← UpdateManager.DoUpdate() ran successfully
[JOURNAL] STEP 2: Opening Bracket_fem1.fem...
[JOURNAL]   Updating FE Model...
[JOURNAL]   FE Model updated with new geometry!  ← UpdateFemodel() ran successfully
[JOURNAL] STEP 3: Switching back to sim part...
[JOURNAL]   Switched back to sim part
[JOURNAL] Starting solve...
[JOURNAL] Solve submitted!
[JOURNAL] Save complete!

Optimization Results (3 Trials with Different Parameters)

Trial 0: tip_thickness=23.48, support_angle=37.21 → stress=197.89 MPa
Trial 1: tip_thickness=20.08, support_angle=20.32 → stress=197.89 MPa (SAME!)
Trial 2: tip_thickness=18.19, support_angle=35.23 → stress=197.89 MPa (SAME!)

Feature Dependency Check

Ran journal to check if any features reference the expressions:

============================================================
CHECKING FEATURE DEPENDENCIES:
============================================================
(empty - no features found that reference tip_thickness or support_angle)

Solution Required

The Bracket.prt parametric model needs to be fixed in NX:

1. Open Bracket.prt in NX
2. Find the sketches/features that define the bracket geometry
3. Link the sketch dimensions to the expressions:
   • Find the dimension that should control tip thickness
   • Edit it to reference the expression: =tip_thickness
   • Find the dimension that should control support angle
   • Edit it to reference the expression: =support_angle
4. Update the part to verify the links work
5. Save Bracket.prt

How to Verify the Fix

After linking the expressions to geometry features:

1. In NX, manually change tip_thickness from 20 to 24
2. Update the part (Ctrl+U)
3. The 3D geometry should visibly change
4. If the geometry changes, the parametric model is now working!

Test to Verify Optimization Works

After fixing the .prt file, run:

cd "C:\Users\antoi\Documents\Atomaste\Atomizer"
echo yes | python examples/test_journal_optimization.py

You should see different stress values for different parameters:

• tip_thickness=20, support_angle=25 → stress = ??? MPa (unique value!)
• tip_thickness=24, support_angle=35 → stress = ??? MPa (different from above!)

What's Been Implemented

The solve_simulation.py journal now includes the COMPLETE regeneration workflow from the user's working journal (journal_with_regenerate.py):

# STEP 1: Switch to Bracket.prt and update geometry
bracketPart = theSession.Parts.FindObject("Bracket")
theSession.Parts.SetActiveDisplay(bracketPart, ...)
markId_update = theSession.SetUndoMark(...)
nErrs = theSession.UpdateManager.DoUpdate(markId_update)  # Rebuild geometry

# STEP 2: Switch to Bracket_fem1 and update FE model
femPart1 = theSession.Parts.FindObject("Bracket_fem1")
theSession.Parts.SetActiveDisplay(femPart1, ...)
fEModel1 = workFemPart.FindObject("FEModel")
fEModel1.UpdateFemodel()  # Regenerate FEM with new geometry

# STEP 3: Switch back to sim and solve
theSession.Parts.SetActiveDisplay(simPart1, ...)
# ... solve and save

This workflow is CORRECT and WORKING - verified by journal output showing all steps execute successfully.

Conclusion

The optimization infrastructure is complete and functional.

The code is ready - it's just waiting for the Bracket.prt file to have its expressions properly linked to the geometry features. Once that's done in NX, the optimization will work perfectly with varying stress results based on the design parameters.

Status: Ready for parametric model fix in NX