Skip to content

fix: continuous Gauss-point loads of a finite-EI line at the free surface - #163

Merged
SMI-Lab-Inha merged 2 commits into
devfrom
fix/static-current-newton-steps
Nov 14, 2026
Merged

SMI-Lab-Inha merged 2 commits into
devfrom
fix/static-current-newton-steps

Conversation

@SMI-Lab-Inha

Copy link
Copy Markdown
Owner

Problem

The statics of a finite-EI line through the free surface could fail at isolated currents. A light lazy-wave cable (OD 31 mm, 0.919 kg/m, EI 0.217 N m², top 0.75 m above the surface, both ends clamped, five buoyancy modules) in a cross current:

Current [m/s] 0.390 … 0.399 0.400 0.401 … 0.410
dev solves fails every static route solves

The load stepping stopped at a drag fraction of 0.997, and Newton with the live drag stagnated at the same residual (1.33e-3) from every start. With 99, 101 or 120 elements instead of 100 it solved.

Cause

Each Gauss point's hydrodynamic load switched on and off at the waterline, so the residual jumped. At 0.400 m/s the third Gauss point of the element through the surface sits at z = 0 in the equilibrium (−0.16 mm at 0.399 m/s, +0.13 mm at 0.401 m/s). The discrete residual then has no root.

Fix

Each Gauss point carries the immersed fraction of its section, linear across one diameter about the surface:

$$w = \min\left(1, \max\left(0, \tfrac12 + \frac{\eta - z_g}{D}\right)\right), \qquad \frac{\partial w}{\partial z_g} = -\frac{1}{D} \text{ in the band}$$

  • Where: the drag, added mass, wave Froude-Krylov load and VIV lift of the Hermite elements (CD_HermiteCable_Immersion), with the derivative in the drag, Froude-Krylov and lift Jacobians.
  • Submerged lines unchanged: a point deeper than $D/2$ has $w = 1$ exactly, so fully submerged elements are integrated as before, to the bit. The EI = 0 path already used a continuous wetted fraction.
  • API: the VIV lift element takes the diameter as an optional argument; without it, it keeps the old switch.
  • Not in scope: attachment point loads keep their node-level switch, since a partial immersion needs the attachment's shape, which the deck does not give.

Tests

  • test_hermite_drag_dynamics E, an element through the surface:

    • the position Jacobian matches central FD (1.6e-10);
    • moved through the surface in 0.1 mm steps, the load changes by at most 3.3e-4 of its size per step (a switch jumped by a Gauss weight, 5/18 or 8/18);
    • a fully submerged element is unchanged to the bit.
  • test_static_surface_crossing (new), the cable above at 21 currents, 0.390–0.410 m/s:

    • every speed solves;
    • the deflection and the top tension grow monotonically;
    • 0.400 m/s lies between its neighbours (1.23319 / 1.23396 / 1.23473 m).

    The same deck fails on dev at 0.400 m/s only.

Checks

  • ctest under both BLAS kernels: the full suite passes with no test changed;
  • Sphinx -W, pre-commit.

…face

The statics of a finite-EI line through the free surface could fail at
isolated currents. Each Gauss point's hydrodynamic load switched on and
off at the waterline, so the residual jumped and an equilibrium with a
point at the surface had no root. A light lazy-wave cable (OD 31 mm,
0.919 kg/m, EI 0.217 N m^2, its top 0.75 m above the surface) in a
cross current solved at 0.399 and 0.401 m/s and failed every static
route at 0.400 m/s: the load stepping stopped at a drag fraction of
0.997, and Newton with the live drag stagnated at the same residual
from every start. 99, 101 and 120 elements solved; at 0.400 m/s the
third Gauss point of the element through the surface sat at z = 0
(-0.16 mm at 0.399 m/s, +0.13 mm at 0.401 m/s).

The drag, added mass, wave Froude-Krylov load and VIV lift of a Gauss
point now carry the immersed fraction of its section, linear across one
diameter about the surface (CD_HermiteCable_Immersion), with its
derivative in the Jacobians. A point deeper than D/2 has the fraction 1
exactly, so fully submerged elements are unchanged to the bit; the EI =
0 path already used a continuous wetted fraction. The VIV lift element
takes the diameter as an optional argument (without it, the old switch).

Gates:
- test_hermite_drag_dynamics E: an element through the surface: the
  position Jacobian matches central FD (1.6e-10), the load changes by
  at most 3.3e-4 of its size per 0.1 mm as the element moves through
  the surface (a switch jumped by a Gauss weight, 5/18 or 8/18), and a
  fully submerged element is unchanged to the bit;
- test_static_surface_crossing: the cable above at 21 currents,
  0.390-0.410 m/s: every speed solves, the deflection and top tension
  grow monotonically, and 0.400 m/s lies between its neighbours (the
  deck fails on dev at 0.400 m/s only).

The full suite passes unchanged under both BLAS kernels.

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 2026-11-14T17:34:59.841558Z b0830d4 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 #35894226 | 📁 Comparing b0830d4 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: b5683e269b

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_HermiteCableDynamic.f90 Resolved
…t the surface

Review: a Gauss point above the instantaneous surface but inside the
band (eta < z < eta + D/2) has a positive immersed fraction, but the
Wheeler-stretched kinematics vanish above eta, so its immersed part
carried no wave Froude-Krylov load or wave drag, and the load still
jumped from about half its value to zero as the centre crossed the
surface.

Such a point now takes the wave velocity and acceleration at the
surface (the kinematics evaluated at z = eta) in the FK and drag
elements; the field gradient stays out of the Jacobian, as documented.
test_hermite_wave_forcing E moves a short vertical element through the
wave surface in steps of D/2000: the FK load and the wave drag change by
at most 2.7e-4 of their largest value per step.

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. Swish!

Reviewed commit: b0830d4292

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 28ece63 into dev Nov 14, 2026
22 checks passed
@SMI-Lab-Inha
SMI-Lab-Inha deleted the fix/static-current-newton-steps branch November 14, 2026 19:31
SMI-Lab-Inha added a commit that referenced this pull request Nov 15, 2026
…164)

A net-buoyant ATTACHMENTS module on a finite-EI line had no static
position near the free surface. Its buoyancy switched off at its node's
height, so its weight in air took it below the surface and its weight
in water above it. The static start stopped with "attachment <k> ...
crossed the still-water level".

The buoyancy, Froude-Krylov force and drag of an attachment now carry
the immersed fraction of the sphere of its volume (of its drag area
without one), the formula a Rigid6 body already uses:
h = clamp(eta - z + r, 0, 2r), phi = h^2 (3r - h)/(4 r^3). The load is
continuous with its slope through the surface.

- Dynamics: the residual takes phi, with the height derivative in the
  position tangent. A node deeper than r keeps phi = 1 exactly, so its
  loads are unchanged to the bit.
- Statics: CD_HermiteCable_Static_Solve takes optional att_node,
  att_buoyancy and att_radius. It adds the buoyancy lost at the surface,
  rho g V (1 - phi), in each Newton iterate, with its stiffness and
  potential. The polish no longer needs the wet/dry fixed point or the
  crossing error. The torsion stage keeps its fixed point over the
  smooth loads.
- Deck waves: a node above the instantaneous surface takes the wave
  kinematics at the surface instead of zero, as the internal waves of a
  cable already did (#163). Line Gauss points interpolated from such
  nodes therefore change too.

The added mass stays in the constant mass matrix. The modal analysis
leaves out the surface's hydrostatic stiffness, a module's as a line's
own.

Gates:
- test_attachment_surface:
  - K1, the fraction: its slope and potential match central FD (1e-8)
    and are continuous at the band edges; r = 0 keeps the old switch.
  - K2, the static solve: with the node in the band the residual gains
    rho g V (1 - phi) and the tangent column matches central FD
    (8.7e-9). Deeper than r the residual and tangent are bit-identical
    to the solve without the term.
- test_static_dry_weight gate 9, the module of the old failure
  (200 kg, 2 m^3, on a slack cable):
  - it now floats 0.348 m below the surface (phi 0.81);
  - the march holds that height over 3 s (drift 0);
  - in 1.5 m, 6 s Airy waves it heaves between -1.21 and +0.48 m
    through its band for 18 s, every step converged.

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