Skip to content

fix: bending forces in the round-off floor of the dynamic tolerance - #158

Merged
SMI-Lab-Inha merged 1 commit into
devfrom
fix/bending-roundoff-floor
Nov 13, 2026
Merged

SMI-Lab-Inha merged 1 commit into
devfrom
fix/bending-roundoff-floor

Conversation

@SMI-Lab-Inha

Copy link
Copy Markdown
Owner

Summary

A finite-EI dynamic step with bending damping (EI|Bb) could fail to converge on a soft line. Newton stagnated just above the tolerance, and the step recovery's smaller steps only made it worse.

It was found on a 20 m vertical riser on a 20 kN/m top tensioner in VIV. That line has EA_eff 4e5 N, 80 elements, Bb 500 N·m²·s and dt 1e-3 s, and its residual stopped at 1.06 times the tolerance.

Cause

The Hermite step's convergence norm divides the residual by a force scale. That scale has a round-off floor, so a residual that no Newton step can reduce still counts as converged. The floor covered only the axial forces:

$$f_\text{floor} = 16\,\epsilon\,\max_e\frac{EA + BA\,\gamma/(\beta\,\Delta t)}{L_0}\,\frac{x_\text{ref}}{\text{tol}}$$

The bending damping takes the curvature rate from the Newmark velocity, whose rounding is $\gamma/(\beta\,\Delta t)$ times that of the coordinates. Its nodal forces therefore round at about

$$\delta f_b \approx \frac{EI + B_b\,\gamma/(\beta\,\Delta t)}{L_0^3}\,\epsilon\,|\mathbf r|$$

On a soft line, where EA/L0 is small (a tensioner in series, a fine mesh), this term is the larger.

Term (failing riser) Value [N/m]
axial $EA/L_0$ 1.6e6
bending damping $B_b\,\gamma/(\beta\,\Delta t)/L_0^3$ 6.4e7

A smaller step raises the damping term further ($\propto 1/\Delta t$), which is why the recovery could not help.

Fix

The floor now takes the larger of the axial and the bending term:

$$f_\text{floor} = 16\,\epsilon\,\max_e\max\left(\frac{EA + BA\,\gamma/(\beta\,\Delta t)}{L_0},\ \frac{EI + B_b\,\gamma/(\beta\,\Delta t)}{L_0^3}\right)\frac{x_\text{ref}}{\text{tol}}$$

The bending term binds only where it is the larger. doc/theory.rst (Hermite convergence) and the CHANGELOG describe the change.

Tests

Check Result
test_hermite_bending_damping_dynamic B6 (new): soft line, EA 4e5 N, Bb 1e4 N·m²·s, dt 1e-4 s old floor: the first step stagnates at 2.2e-7 > 1e-8 and fails; now 200 steps converge and the motion stays bounded
The failing riser decks (two variants, Bb 500 and 510) fail on dev at t = 2.67 s and 2.76 s; run to the end now
ctest, both BLAS kernels 421/421, 421/421
Debug -fcheck subset (bending, VIV, Hermite drag, restart, checkpoint) 28/28
Every example and test deck against dev (Python dump) 1685 arrays over 70 decks bit-identical
Sphinx -W, pre-commit pass

A finite-EI dynamic step with bending damping (EI|Bb) could fail on a
soft line: Newton stagnated just above the tolerance and the step
recovery's smaller steps made it worse. Found on a 20 m riser on a
20 kN/m tensioner (EA_eff 4e5 N, 80 elements, Bb 500 N m^2 s, dt 1e-3 s)
in VIV: the residual stopped at 1.06 times the tolerance.

The bending damping takes the curvature rate from the Newmark velocity,
whose rounding is gamma/(beta dt) times that of the coordinates, so its
nodal forces round at about Bb gamma/(beta dt) eps |r|/l0^3. The force
scale's round-off floor covered the axial forces alone,
(EA + BA gamma/(beta dt)) eps |r|/l0. It now takes the bending forces,
(EI + Bb gamma/(beta dt)) eps |r|/l0^3, too; that term binds only where
it is the larger, so every example and test deck gives bit-identical
outputs (1685 arrays over 70 decks).

Test: test_hermite_bending_damping_dynamic B6, a soft line (EA 4e5 N)
with Bb 1e4 N m^2 s at dt 1e-4 s. On the old floor its first step
stagnates at 2.2e-7 against the tolerance 1e-8; now 200 steps converge
and the motion stays bounded.

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 13, 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 2026-11-13T17:12:37.299626Z 4a50111 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.

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. You're on a roll.

Reviewed commit: 4a501117d2

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".

@read-the-docs-community

Copy link
Copy Markdown

Documentation build overview

📚 CableDyn | 🛠️ Build #35873921 | 📁 Comparing 4a50111 against latest (789cb6d)

  🔍 Preview build  

13 files changed · ± 13 modified

± Modified

@SMI-Lab-Inha
SMI-Lab-Inha merged commit 1847a0d into dev Nov 13, 2026
25 of 26 checks passed
@SMI-Lab-Inha
SMI-Lab-Inha deleted the fix/bending-roundoff-floor branch November 13, 2026 19:47
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