Skip to content

fix(torsion): coupled held lines step, body passes converge, a lazy wave in current starts at any pretwist - #82

Merged
SMI-Lab-Inha merged 3 commits into
devfrom
fix/torsion-campaign
Nov 3, 2026
Merged

SMI-Lab-Inha merged 3 commits into
devfrom
fix/torsion-campaign

Conversation

@SMI-Lab-Inha

Copy link
Copy Markdown
Owner

Summary

Three torsion defects from the 0.4.0 robustness campaign (all present on dev), each with a gate that fails on the old code.

  • Strong torque-tension coupling (torsion_coupling_still). With K >= 0.85 sqrt(EA GJ) (and -0.8 with one end free in torsion) a held line in exact static equilibrium failed its dynamic step within 0.05-0.9 s ("Newton did not converge, ||G|| = 2.4e-8 > tol = 1e-8"). The round-off floor of the step's convergence norm took only the kernel's EA - K^2/GJ; it now also takes the coupling's share of the axial force and of the element torque, whose twist -(K/GJ)(l - l0) is formed from coordinates. Held lines with K up to 0.99 sqrt(EA GJ), in either sense and with one end free, hold at the default dtM and tolerance.
  • Static body passes of a cable restrained in torsion between two Rigid6 bodies (torsion_body_passes). The passes compared the change of the cable's end loads with 1e-10 of their scale, below the resolution of the core's body balance (1e-9 of the bodies' net weight): at 360 deg (Rigid ends) and 300 deg (Pinned) they stalled near 2e-9 and the deck stopped, with advice (bodyIC deck) that was not the remedy. They now stop at the resolution the core leaves; the Rigid 360 deg case converges in 6 passes (torque 4886.24 N m) and the pretwist sweep 120-720 deg converges for both end kinds.
  • A lazy wave restrained in torsion in an in-plane current (torsion_current_start). With 25 buoyancy modules in a 0.5 m/s current its untwisted static state, solved in its vertical plane, is unstable out of that plane on its mesh, which the deck without torsion accepts with a note; the torsion stage refused the twisted state although the twist added no negative stiffness mode ("torsion continuation stalled at Phi = 0 (target 0)" at pretwist 0, an unstable equilibrium after a failed Newton solve at 360 deg). A twisted state with no more negative modes than its untwisted one is now kept, and the note names the instability as the untwisted state's. Two more causes made this start depend on the pretwist and on the BLAS kernel's round-off. First, the coarse branch-selection build (and the other static helper builds) ran the torsion stage, and its twisted state seeded the untwisted solve on the deck mesh: 180 deg stopped in the attachment polish, and 360 deg needed the polish's fallbacks and stopped with OPENBLAS_CORETYPE=Prescott. Second, each pass of the attachment fixed point after the first applied the drag of the last twisted shape in full at the untwisted start, so 270 deg and more stopped before any twist. Helper builds now solve the untwisted line, and the change of the attachment loads is ramped with the imposed twist (new f_nodal_twist of CD_HermiteCable_Static_Solve). Pretwists from 0 to 720 deg now start without fallbacks, with the same torques on Haswell and Prescott kernels, proportional to the pretwist.

Also: the "unresolved/kinked equilibrium" refusal names the factor to refine the section's NumSegs by.

Checks

ctest 356 of 356 (OpenBLAS Prescott kernel); checked Debug build (-fcheck=all) on the 26 torsion tests; torsion_current_start deck at pretwist 0-720 deg on the Haswell and Prescott kernels; example A/B 53 of 53 identical; pre-commit (fprettify-stable), Sphinx -W.

…ave in current starts

Three torsion defects of the 0.4.0 robustness campaign (all on dev):

- Strong torque-tension coupling: with K >= 0.85 sqrt(EA GJ) (and -0.8
  with one end free) a held line in exact static equilibrium failed its
  dynamic step ("||G|| = 2.4e-8 > tol = 1e-8"): the round-off floor of the
  convergence norm took only the kernel's EA - K^2/GJ. It now takes the
  coupling's share of the axial force and of the element torque (whose
  twist is formed from coordinates). Gate torsion_coupling_still: K up
  to 0.99 sqrt(EA GJ), either sense, one end free; fails on the old code.
- Static body passes of a cable restrained in torsion between two Rigid6
  bodies stalled near 2e-9 at 360 deg (Rigid) and 300 deg (Pinned): the
  1e-10 pass tolerance sat below the resolution of the core's body
  balance. The passes now stop at that resolution (four times the core's
  residual load), and the failure advice no longer suggests bodyIC deck.
  Gate torsion_body_passes: the pretwist sweep converges (Rigid 360 deg
  in 6 passes, torque 4886.24 N m); fails on the old code.
- A lazy wave with 25 modules restrained in torsion in a 0.5 m/s in-plane
  current was refused by the torsion stage ("stalled at Phi = 0") although
  the twist added no negative stiffness mode to its untwisted state,
  which is unstable out of its plane and accepted by the deck without
  torsion. A twisted state with no more negative modes than its untwisted
  one is now kept and named as such. Gate torsion_current_start (pretwist
  0 and 360 deg); fails on the old code.

Also: the "unresolved/kinked equilibrium" refusal names the factor to
refine the section's NumSegs by.

Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
…BLAS kernel

The start of the lazy wave restrained in torsion in an in-plane current
depended on the pretwist and on the round-off of the BLAS kernel:

- The static helper builds (coarse branch selection, auxiliary-weight
  seed, friction reference, no-current diagnosis) ran the torsion stage,
  and the twisted coarse state seeded the untwisted solve on the deck
  mesh. Pretwist 180 deg stopped in the attachment polish; 360 deg
  needed the polish's fallbacks and stopped with
  OPENBLAS_CORETYPE=Prescott. Helper builds now solve the untwisted line.
- Each pass of the attachment fixed point after the first applied the
  drag of the last twisted shape in full at the untwisted start, which
  pushed the out-of-plane-unstable untwisted state away before any twist
  (270 deg and more). The load change is now ramped with the imposed
  twist (f_nodal_twist of CD_HermiteCable_Static_Solve).

Pretwists 0 to 720 deg now start without fallbacks, with the same
torques on the Haswell and Prescott kernels, proportional to the
pretwist. torsion_current_start sweeps 0/180/360/720 deg and checks
both.

Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
@SMI-Lab-Inha

Copy link
Copy Markdown
Owner Author

@codex review

@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Nov 3, 2026 •

Copy link
Copy Markdown

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-11-03T06:42:31.859928Z 9d0971b Manual request
ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

@read-the-docs-community

read-the-docs-community Bot commented Nov 3, 2026 •

Copy link
Copy Markdown

Documentation build overview

📚 CableDyn | 🛠️ Build #35604455 | 📁 Comparing 9d0971b against latest (fd1936d)

  🔍 Preview build  

33 files changed · ± 33 modified

± Modified

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. Can't wait for the next one!

Reviewed commit: 1bdbb754e4

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

The pretwist sweep runs four independent decks; one after another they
took 322 s in a local Debug build and passed the 600 s test timeout on
the CI Debug runners. They now run concurrently (158 s locally in
Debug, 26 s in Release), and the timeout is 900 s, as for the other
long driver tests.

Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
@SMI-Lab-Inha

Copy link
Copy Markdown
Owner Author

@codex review

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. Another round soon, please!

Reviewed commit: 9d0971bf64

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

@SMI-Lab-Inha
SMI-Lab-Inha merged commit 3a15aef into dev Nov 3, 2026
21 checks passed
@SMI-Lab-Inha
SMI-Lab-Inha deleted the fix/torsion-campaign branch November 3, 2026 08:32
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant