Skip to content

feat: a finite-EI line may end on a Free point (a free cable end) - #159

Merged
SMI-Lab-Inha merged 4 commits into
devfrom
feat/finite-ei-free-end
Nov 14, 2026
Merged

SMI-Lab-Inha merged 4 commits into
devfrom
feat/finite-ei-free-end

Conversation

@SMI-Lab-Inha

Copy link
Copy Markdown
Owner

Summary

A finite-EI line can now end on a Free point. Before this, there was no deck for a free-hanging cable or riser with a clump weight, which is the set-up of forced-oscillation and tow tests on power cables. The single-cable route held both end positions and refused the point's loads. With a Free point present, the deck went to the multibody march, which holds cable ends.

When a Free point becomes a free cable end

All of these must hold:

  • the point ends exactly one finite-EI line, as its End B;
  • that line's End A is a Coupled or Vessel point (a still hang-off is a Coupled point without motion);
  • the deck is standalone, its lines are all finite-EI, and it has no BODIES, RODS or other Connect/Free point.

What changes

Stage Behaviour
Loads The point's Mass, Vol, CdA and CA act on the End B node as an end attachment: weight and buoyancy, added mass, fluid inertia, drag.
Statics The end is first held on the chord from End A towards the deck position, at the line's length stretched by its hanging weight. This taut straight line is the seed; a vertical span of exactly the line's length has no catenary seed. The end is then released with the attachment polish's warm-started Newton solve (new release option), so the run starts at the end's rest position.
Dynamics Only End A's three positions are held.
Outputs Point<P>p… channels read the line's End B node.

The seed length is

$$L\left(1 + \frac{W_B + \sum_i w_i L_i}{EA_{\min}}\right)$$

where $W_B$ is the point's submerged weight and $w_i$ the submerged weight per metre of section $i$.

The line must also be pinned in bending at both ends, and the end must hang (point and line net heavy). A torsion restraint at one end is not solved, since a free end carries no torque; the initialisation note says why, as dev already does for a line with two moving ends. If any Free point of a deck is not such an end (a clamped or buoyant end, a second Free point, a Connect point), nothing is promoted: the deck behaves exactly as on dev, including its existing refusal messages.

Host-driven decks (OpenFAST, the C API) keep refusing a finite-EI cable on a Free point. The Python deck reader takes the same rule.

Checks

tests/test_free_end_deck.f90 uses a 7 m cable (Diam 0.048 m, 2.8 kg/m, EA 1e8 N) with a 200 kg clump (0.02548 m³, CdA 0.06 m², CA 1).

Case Check Result
Still water Top tension equals the submerged weight of line and clump within 1e-6 relative
Still water The end hangs one stretched length below the top, with stretch $(W_B L + w L^2/2)/EA$ within 1e-7 m
Still water Nothing moves over the run within 1e-10 m
0.5 m/s current End position against the same deck as an EI = 0 line on the point-system route 0.134357 vs 0.134353 m at EI 3 N m² (gate 2e-5 m)
0.05 m top sway at 0.05 Hz End amplitude ratio against the Rayleigh estimate for a hanging string with its end mass 1.106 vs 1.104 (gate 1 %), in phase
Not promoted Clamped end, net-buoyant end, second Free point dev's refusal messages, unchanged

As EI falls, the end position in current converges to the EI = 0 result:

EI (N m²) 3000 300 30 3 EI = 0 route
end x (m) 0.134530 0.134381 0.134359 0.134357 0.134353

python/tests/test_deck_native_parity.py::test_free_cable_end_matches_the_driver checks that the Python reader and the native driver agree on the two accepted and three refused decks.

Gates

  • ctest: both BLAS kernels (default and Prescott)
  • Debug -fcheck subset
  • pytest
  • ruff, mypy
  • sphinx-build -W
  • pre-commit

Two test expectations change: a Coupled→Free finite-EI deck, plain or with one torsion-restrained end, used to be refused by the multibody march and now runs as a free end, with the same verdict for both (test_torsion_scope_rules_follow_the_native_checks). Every other existing deck is unchanged: a deck without a free cable end never reaches the new code. The attachment polish's new release argument defaults to false.

A finite-EI line could not end on a Free point: the single-cable route
held both end positions and refused the point's loads, and with a Free
point the deck went to the multibody march, which holds cable ends. A
free-hanging cable or riser with a clump weight (forced-oscillation and
tow tests of power cables, installation, a dropped line) had no deck.

A Free point that ends exactly one finite-EI line as its End B, from a
Coupled or Vessel End A, on a standalone deck whose lines are all
finite-EI and that has no BODIES, RODS or other Connect/Free point, is
now that line's free end:
- the point's Mass, Vol, CdA and CA act on the End B node as an end
  attachment (weight and buoyancy, added mass, fluid inertia, drag);
- the static solve holds the end first on the chord from End A towards
  the deck position, at the line's length stretched by its hanging
  weight (the taut seed; a vertical span of exactly the line's length
  has no catenary seed), then releases it with the attachment polish's
  warm-started Newton solve (new option release), so the run starts at
  the end's rest position;
- the dynamics hold End A alone;
- Point<P>p channels read the line's End B node.
The line must be pinned in bending at both ends and the end net heavy;
a torsion restraint at one end is noted and not solved. A deck in which
any Free point is not such an end, and a host-driven deck, keeps its
behaviour and its refusal messages. The Python deck reader takes the
same rule.

Checks (tests/test_free_end_deck.f90, a 7 m cable with a 200 kg clump):
- still water: top tension = submerged weight to 1e-6 relative, the end
  one stretched length below the top to 1e-7 m, nothing moves;
- 0.5 m/s current: the end rests where the EI = 0 route puts the same
  deck's Free point, within 2e-5 m at EI 3 N m^2 (0.134357 against
  0.134353 m), converging as EI falls;
- 0.05 m sway of the top at 0.05 Hz: the end follows in phase, the
  amplitude ratio within 1 % of the Rayleigh estimate (1.106 against
  1.104);
- a clamped end, a buoyant end and a second Free point keep their
  refusal messages;
- python/tests/test_deck_native_parity.py: the reader and the driver
  agree on the accepted and refused decks.

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 14, 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 2026-11-14T09:17:14.149011Z df7108a 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 14, 2026 •

Copy link
Copy Markdown

Documentation build overview

📚 CableDyn | 🛠️ Build #35888392 | 📁 Comparing df7108a against latest (789cb6d)

  🔍 Preview build  

13 files changed · ± 13 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: 5192790ef9

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
Review: the promoted point reads Fixed, so a stretched chord seed below
a flat seabed was refused by the anchor seabed check before the free
end's equilibrium was solved, although the seed is only a starting
position (a line longer than the depth whose end the current lifts
clear of the seabed).

- check_fixed_point_above_seabed skips a free cable end.
- On a flat seabed a seed below the seabed is placed on it at the same
  stretched length, out along the deck chord's horizontal direction, so
  the held seed is still the taut straight line.
- An end whose point is net heavy and that comes to rest on the seabed
  is refused by name: an attachment has no seabed contact of its own on
  a finite-EI line, so the point would sink into the line's contact
  (a 200 kg clump on a 6 m deep seabed came to rest 0.8 m below it).
  A bare end rests on the line's own contact.
- A bathymetry deck keeps its behaviour (no promotion), as the seed is
  placed against the flat seabed only; the Python reader mirrors it.

tests/test_free_end_deck.f90 F5: a 5 kg end in a 0.8 m/s current over a
7.3 m deep seabed (the vertical seed 7.5 m) rests 1.2 m above it, 4.19 m
downstream; the 200 kg clump on a 6 m deep seabed is refused by name.

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 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: b846a31344

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
Comment thread python/cabledyn/deck_file.py Resolved
Review:
- The promoted end attachment applied the point's CdA to the normal
  relative velocity only (CdAx 0), while a Free point's drag acts on the
  whole relative velocity (point_environment_force): a hanging clump in
  heave or axial flow lost its drag, and oblique flow drag differed.
- The Python reader counted a numeric zero END CONNECTIONS stiffness
  (0, 0.0) as a restraint, where the native reader maps it to pinned
  (bending) and free (torsion), so it refused decks the driver accepts.

The attachment drag kernel takes an optional isotropic flag, the
point's law rho CdA |w| w / 2 with its exact Jacobian (no tangent
dependence); CD_HermiteCable_Dyn_Set_Attachments and
CD_HFMF_Set_Attachments carry it per attachment, and the deck static
drag uses it too. The promoted attachment marks it internally (CdAx -1,
which a deck row cannot give); the smeared continuation start takes
CdAx = CdA. The Python check reads a numeric zero as pinned or free.

tests/test_free_end_deck.f90 F6: in a vertical 0.5 m/s current along the
hanging line the top tension grows by the clump's rho CdA w^2 / 2 =
7.69 N (to 1e-3 N). The parity test accepts a numeric zero End B
stiffness on both sides.

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 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: 5fe0a11386

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
Review: the promoted point's loads sit on the End B node as an
attachment, and CD_HermiteCable_Dyn_End_Force adds every attachment on
the end node to the end force. At the free end that attachment is the
body the force acts on, so its loads cancelled the line's: a hanging
clump at rest read AnchTen, the End B nodal tension and Point<P>Fz of
about zero instead of its submerged weight, unlike the EI = 0 route and
the documented "line load a free point balances".

CD_HermiteCable_Dyn_Set_Attachments (and CD_HFMF_Set_Attachments) take
an optional point_load flag per attachment: the attachment stays in the
equations of motion, and the end force leaves it out. The deck driver
sets it on the promoted attachment.

tests/test_free_end_deck.f90 F1: in still water AnchTen1 and Point2Fz
read the clump's submerged weight (1705.21 N, to 1e-6 relative) and
Point2Fx zero, the same values as the deck run as an EI = 0 line.

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. Delightful!

Reviewed commit: df7108abab

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 43fcba4 into dev Nov 14, 2026
22 checks passed
@SMI-Lab-Inha
SMI-Lab-Inha deleted the feat/finite-ei-free-end branch November 14, 2026 11:44
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