Skip to content

fix(statics): an EI = 0 residual cycling inside its round-off floor is converged - #122

Merged
SMI-Lab-Inha merged 2 commits into
devfrom
fix/ei0-static-floor-cycle
Nov 8, 2026
Merged

SMI-Lab-Inha merged 2 commits into
devfrom
fix/ei0-static-floor-cycle

Conversation

@SMI-Lab-Inha

Copy link
Copy Markdown
Owner

A suspended composite EI = 0 line in a current reported "no admissible static equilibrium" depending only on the last digits of its coordinates. The base deck solved, but 13 of 32 small translations of it failed. Translated point systems failed the same way.

Cause

CableDyn_Static.f90 accepted a residual inside its round-off floor only while the residual stayed flat. Here the iterates alternate between 9.49e-5 and 8.77e-5 N, against a floor of 3.1e-3 and a tolerance of 2.6e-5. Every stage therefore ran its whole iteration budget (1268 iterations) and failed.

Fix

A residual inside the floor that sets no new minimum over the stall window now counts as converged.

Evidence

  • New ei0_static_floor_cycle: the 32 translations. Before the fix 13 fail, on every OpenBLAS kernel. After it none fail, and the tensions are identical.
  • Suites: CTest 369/369 on both kernels; pytest passes.
  • Examples: all 54 are bit-identical.

The CHANGELOG entry goes into the batch CHANGELOG PR.

The EI = 0 static Newton solve converges a residual that is inside the
round-off floor of its nodal forces but above the relative tolerance only
when the residual stays flat over the stall window. Inside the floor the
iterates can also alternate between two values (the rounding of the last
digits), which the flat test never sees: the Levenberg-Marquardt stages
then ran out of iterations and the line had no admissible equilibrium.
Whether a deck solved depended on the last digits of its coordinates: 13 of
32 small translations of a suspended three-section line in a 0.67 m/s
current failed (the residual alternating between 9.49e-5 and 8.77e-5 N,
with a floor of 3.1e-3 N and a tolerance of 2.6e-5 N), and translated copies
of point systems failed in their line solves.

A residual inside the floor that sets no new minimum over the stall window
is now converged as a flat one is. Every example deck gives the same output
as before.

The new ei0_static_floor_cycle test solves the 32 translated decks and
requires the same end tensions from each to 1e-7.

Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
The [Unreleased] entries of the open changes are added together in one
change, so that they do not conflict with each other.

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 8, 2026 •

Copy link
Copy Markdown
Codex Review Summary: ✅ Completed

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

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-11-08T15:15:10.510663Z 5f905bc 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

Copy link
Copy Markdown

Documentation build overview

📚 CableDyn | 🛠️ Build #35735027 | 📁 Comparing 5f905bc against latest (e8f88f5)

  🔍 Preview build  

6 files changed · ± 6 modified

± Modified

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. Keep it up!

Reviewed commit: 5f905bceb6

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 2f4d2f5 into dev Nov 8, 2026
22 checks passed
@SMI-Lab-Inha
SMI-Lab-Inha deleted the fix/ei0-static-floor-cycle branch November 9, 2026 08:55
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