Skip to content

fix(recovery): spread the touchdown node's floor reaction over its grounded stretch - #109

Merged
SMI-Lab-Inha merged 1 commit into
devfrom
fix/touchdown-node-channels
Nov 8, 2026
Merged

SMI-Lab-Inha merged 1 commit into
devfrom
fix/touchdown-node-channels

Conversation

@SMI-Lab-Inha

Copy link
Copy Markdown
Owner

The node tension recovered at the touchdown node of a finite-EI cable (the default OutputRecovery equilibrium) had a local error that fell only at first order with the element length. The size of the error depended on where the touchdown point lay in its element. It also stepped when a node grounded or lifted off.

Cause

The equilibrium recovery spreads each nodal seabed reaction over the grounded half-elements beside the node. The touchdown element, which is on the floor at one end only, took none of the first grounded node's reaction, wherever the touchdown point was.

Fix

  • Grounded stretch: the touchdown element is now grounded from its grounded node to the touchdown point. That point is where the clearance, interpolated linearly between the element's two nodes, reaches the contact onset; the stretch is at most half the element.
  • Reaction spread: each node's reaction is spread uniformly over the grounded part of its two half-elements and shared by length. Exact shape integrals over [0, x] replace the fixed half-element constants, and reproduce them at x = 1/2.
  • Continuity: the stretch reaches the half-element as the suspended node grounds, and vanishes with the reaction as the grounded node lifts off. The outputs are therefore continuous.

This is an output-recovery change only. The solution, end forces and touchdown channels are unchanged.

Evidence

Worst local tension error over all touchdown positions, lazy wave in current at 270 N:

Element size Before After
1.6 m 4.27 N 2.12 N
0.8 m 1.89 N 0.70 N
0.4 m 1.00 N 0.21 N
0.2 m 0.42 N 0.05 N
  • Convergence order: the error now falls at second order instead of first.
  • Quasi-static march: the 1.4 N step at a grounding node is gone.
  • OutputRecovery element: left as it is. It is the legacy pointwise definition, with documented oscillation.
  • Coarse-mesh dynamic chatter: the chatter seen on coarse meshes in dynamics is a real axial wave. It also appears in the fairlead force, at the line's axial period. It is the same before and after this change, and it converges with the mesh (table in doc/outputs.rst).

Changed outputs

  • .out time series: every one of the 61 example decks gives bit-identical .out time series.
  • .static.out / .range.out: only the touchdown-node values change. Tension moves by at most 0.44 N; bend moment at the first grounded node moves by up to 17 N·m on the 3.3 m mesh of lozon_gomex80_power_cable_motion.dat, where both the old and new values are unresolved.

Tests

  • New driver_touchdown_convergence: it uses nine meshes at each of 1.6 / 0.8 / 0.4 m against a 2048-element reference. It requires the error to fall by at least 2.5× from 0.8 to 0.4 m and to stay below 0.35 N.
    • Before the change: it fails, ratio 1.89, 1.0 N.
    • After the change: it passes, ratio 3.66, 0.19 N.
  • Full CTest, Release: 366/366 on the default kernel and on OPENBLAS_CORETYPE=Prescott.
  • Debug: the touchdown-related subset passes.
  • pytest: passes.

…ounded stretch

The equilibrium recovery of the finite-EI node outputs spreads each nodal seabed
reaction over the grounded half-elements beside the node. The touchdown element,
on the floor at one end only, took none of the first grounded node's reaction,
wherever the touchdown point lay in it. The node tension next to touchdown then
carried a local error that depended on that position and fell only at the first
order with the element length: at most 4.3, 1.9, 1.0 and 0.42 N at 1.6, 0.8, 0.4
and 0.2 m elements on a lazy-wave cable at 270 N. The share also switched when a
node grounded, so the node outputs stepped by up to about 1 N in a quasi-static
march as the touchdown point crossed a node.

The touchdown element is now grounded from its grounded node to the touchdown
point, where the clearance interpolated linearly between its two nodes reaches
the contact onset height (at most its half), and takes the reaction of that
stretch: a node's reaction is spread uniformly over the grounded part of its two
half-elements and shared by that length. The stretch reaches the half-element as
the suspended node reaches the floor and vanishes with the reaction as the
grounded node lifts off, so the outputs vary continuously. The local error now
falls at the second order (2.1, 0.7, 0.2, 0.05 N). The solution, the end forces
and the touchdown channels are unchanged.

driver_touchdown_convergence sweeps nine meshes at each of three element sizes so
that the touchdown point falls at every position in its element, and requires
the local error to fall by at least 2.5 from 0.8 to 0.4 m elements and to stay
below 0.35 N there; it fails on the previous recovery (ratio 1.89, 1.0 N).

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 2026-11-08T07:12:53.745223Z b8d1e2f 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 #35729860 | 📁 Comparing b8d1e2f against latest (e8f88f5)

  🔍 Preview build  

3 files changed
± changelog.html
± outputs.html
± theory.html

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. Hooray!

Reviewed commit: b8d1e2f525

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 0b8eee3 into dev Nov 8, 2026
22 checks passed
@SMI-Lab-Inha
SMI-Lab-Inha deleted the fix/touchdown-node-channels branch November 9, 2026 08:56
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