Skip to content

fix(output): report the section under a bend stiffener - #89

Merged
SMI-Lab-Inha merged 4 commits into
devfrom
fix/stiffener-node-curvature
Nov 7, 2026
Merged

SMI-Lab-Inha merged 4 commits into
devfrom
fix/stiffener-node-curvature

Conversation

@SMI-Lab-Inha

Copy link
Copy Markdown
Owner

Summary

Under a tapered bend stiffener the bending stiffness is one value per element, so every node sits on a small stiffness step that the section does not have. The node outputs took the softer side, which overstated the curvature by about h |EI'| / (2 EI): first order in element length, 3.3 % at 0.1 m elements. The element outputs carried a bias of the same size, of either sign depending on the deck.

  • Node outputs: a stiffened line keeps EI(s) at every node, one limit per side. The larger-side rule compares those limits, so a real step (the bare tip, a step between stiffener rows, a junction of line types) stays a step, and no tolerance on the stiffness ratio is needed. Curv, CurvX, CurvY, BendMom, StfMom, .static.out and the range graphs follow.
  • Element outputs: .elements.out peaks, and OutputRecovery element on sleeved elements, report the section moment over EI(s).
  • Lines without a stiffener are bit-identical.

Result changes

lazy_wave_bend_stiffener.dat, 0.152 m elements, static: node Curvature and BendMoment change at nodes inside the stiffener by -0.6 to -4.4 %; .elements.out peaks by -1.1 to +4.4 %. Positions, tensions and everything outside the sleeve are bit-identical.

Checks

Local error under the taper against the planar elastica, floored at 0.1 % of the root curvature:

Element size Nodes before Nodes after .elements.out peaks after
0.2 m 6.67 % 0.97 % 0.97 %
0.15 m 4.92 % 0.49 % 0.49 %
0.1 m 3.30 % 0.24 % 0.24 %
0.05 m 1.61 % 0.18 % 0.18 %
  • driver_bend_stiffener gains this gate, swept over element size; it fails without the change.
  • CTest 359 of 359 on the default kernel and with OPENBLAS_CORETYPE=Prescott; pytest passes; no new compiler warnings.

The CHANGELOG entry lands with the release batch.

The node outputs divided the section moment by the element stiffness on
the side giving the larger curvature. Under a taper that stiffness is one
value per element, so it steps at every node although the section does
not: the softer element always won, and the curvature and the cable's
moment were high by about h |EI'| / (2 EI), first order in the element
length.

The line now keeps EI(s) at each node from the stiffener rows, one limit
per side (CD_Stiffener_Node_EI, on the final mesh), and node_values reads
those. The limits differ only at a real step of the section: the bare tip,
rows that do not match and two line types, where the larger-side rule
still decides. No threshold on the stiffness ratio is needed. Curv, CurvX,
CurvY, BendMom, StfMom, the static profile and the range graphs all take
the values from node_values; a line without a stiffener is unchanged.

driver_bend_stiffener gains a local gate over a sweep of element sizes,
the identities between the channels and the real steps. The error on
0.1 m elements falls from 3.3 % to 0.24 % of the local curvature.

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

The peaks of .elements.out and the node values of OutputRecovery element
read the element's interpolation. On an element with a sleeve that
interpolation bends under one stiffness, so its curvature is no section's:
it differs from the section's by h |EI'| / (2 EI), high where the curvature
falls toward the tip and low where it rises, and EI_e times it is the
linear fit of the moment, low at the element ends by h^2 M''/12.

An element with a sleeve now reports the section. Its peak is the largest
|M(u)|/EI(u) along it, with M(u) the quadratic through the recovered
moments of the end nodes that keeps the mean of the fit, and a row end or
tip inside the element kept as a step of EI(u). OutputRecovery element
takes the recovered moment over EI(s) on such an element, with the exact
trace on every other element. bend_check and element_range_graph read the
table and follow. The geometric traces stay available as
CD_HermiteCable_Dyn_Curvature_Exact and in the mesh diagnostics.

A line without a stiffener is unchanged bit for bit. driver_bend_stiffener
gates both outputs under the taper over the same element sizes: on 0.1 m
elements the error falls from 3.1 % to 0.24 % of the local curvature.

Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
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 7, 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 2026-11-07T13:41:50.061903Z 766ca6e 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 7, 2026 •

Copy link
Copy Markdown

Documentation build overview

📚 CableDyn | 🛠️ Build #35719303 | 📁 Comparing 766ca6e against latest (3d04008)

  🔍 Preview build  

6 files changed · ± 6 modified

± Modified

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 72f2908d1f

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".

Comment thread src/CableDyn_DeckDriver.f90 Resolved
The peak of an element under a bend stiffener divided the recovered moment
by EI(s) everywhere. That moment carries an error of order w L0^2/12 that
does not depend on EI, so on a sleeve below the stiffness that resolves it
the peak was noise: 24 times the curvature of the element's nodes on a
100 m soft sleeve of the coarse lazy wave. The nodes already fall back on
the interpolation's curvature there, and the peak now does the same, point
by point, with the same check on EI(s) and the same EI_e/EI(s) scale.

The peak path also takes the tangent from the element's midpoint, which
the curvature call has checked, in place of the chord, which vanishes on a
folded element, and stops on moments that are not finite instead of
reporting a zero peak.

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. Hooray!

Reviewed commit: 766ca6e749

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 6545ed0 into dev Nov 7, 2026
21 checks passed
@SMI-Lab-Inha
SMI-Lab-Inha deleted the fix/stiffener-node-curvature branch November 7, 2026 15:35
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