Skip to content

feat: OrcaFlex "as laid" seabed friction in statics - #17

Merged
SMI-Lab-Inha merged 10 commits into
devfrom
feat/static-friction
Oct 16, 2026
Merged

SMI-Lab-Inha merged 10 commits into
devfrom
feat/static-friction

Conversation

@SMI-Lab-Inha

Copy link
Copy Markdown
Owner

Summary

Seabed friction in the static solve, following OrcaFlex's "As laid" policy, as an opt-in option. The default is unchanged.

Problem. Seabed friction had no effect on the static solve. The friction springs are anchored to the frictionless still-water layout, so a grounded run on a slope with tan θ < μ, or one laid with surplus length, still slid or folded. An EI = 0 line on a 5° slope with μ = 1 folded 24 m past its anchor, exactly as with μ = 0, and a finite-EI cable on a 10° slope failed outright.

What OrcaFlex does (sources cited in doc/theory.rst):

  • Policy: the statics friction policy is None, As laid or Restart.
  • As laid: the line is assumed laid from its bottom end along the lay azimuth, following the seabed, with its targets spaced by the unstretched segment lengths and the as-laid tension. Friction acts toward these positions, and the dynamics start from the statics targets.
  • Sources: Line data: Statics, Friction theory.

New options.

  • staticsFriction asLaid|none. The default is none: the previous behaviour, and that of MoorDyn, which is conservative for anchor loads. Every example and test deck is byte-identical under it.
  • layAzimuth / layAzimuth<ID>: the lay direction. The default runs from anchor to fairlead.
  • asLaidTension / asLaidTension<ID>: default 0.
  • Per-line values override the global ones.

Design.

  • Reference geometry: CD_Static_As_Laid_Reference lays the reference from the line's lower end on a flat seabed or bathymetry. On a slope each target carries the node's static penetration, so a line resting where it was laid carries no friction.
  • Friction law: the regularised law of the dynamics, isotropic or anisotropic, in still water or in a current.
  • Line families:
    • EI = 0: an as-laid seed is tried first.
    • Finite-EI: the friction rides on the current carrier and is seeded from the EI = 0 equilibrium.
    • Off-plane azimuth: an azimuth off the chord plane makes the finite-EI solve 3D.
  • Dynamics: the friction anchors continue the static spring forces, so there is no jump at t = 0.
  • Coverage: the OpenFAST aggregate, the C API and the Python deck reader/writer/builder share it. The routes that cannot apply it reject asLaid by name.

Results (with asLaid)

Case Before After
EI = 0, 5° slope, μ = 1 folds 24.0 m past the anchor; FairTen 714.2 kN holds where laid; FairTen 622.9 kN; friction ≤ μN at every grounded node; held run drifts 1.5e-10 of FairTen
Finite-EI, 10° slope, 650 m fails solves and holds
Finite-EI, layAzimuth 45° — 3D solve, held at rest
Flat seabed, laid at its run tension — FairTen within 6e-6 of frictionless

As an illustration of the effect, the IEA-15 mixed example with asLaid has a chain AnchTen of 368 kN instead of 1352 kN, because friction holds back a run laid slack and pulled taut. This is why the default stays none.

Known limit. A 700 m finite-EI cable laid past the point under its fairlead must form a hook at touchdown, which the seeds do not reach. Another layAzimuth solves it (documented in troubleshooting).

Tests

  • tests/test_static_friction_as_laid.py (fails on the base):
    • the slope cases (EI = 0 and finite-EI) with mobilised friction;
    • held runs;
    • flat-seabed equivalence;
    • off-plane and flipped azimuths;
    • cross-slope lateral force against the EI = 0 route;
    • per-line precedence;
    • anisotropic friction;
    • a multi-section line;
    • input rejection.
  • Python: reader, writer and builder tests.
  • Full suite, Windows, gfortran, Release, slow tier included: 260/260. Python: 1958 passed. pre-commit run --all-files passes.
  • Default: byte-compare of all 71 examples and test decks against the base build under the default: identical.

Checklist

  • pre-commit run --all-files passes
  • ctest --test-dir build --output-on-failure passes
  • python -m pytest tests python/tests passes (if Python or validation records changed)
  • VALIDATION.md updated if a validation result changed — no result changes under the default
  • CHANGELOG.md updated under [Unreleased] (heading added if missing) for user-visible changes
  • Documentation in doc/ updated for changed inputs, options, or outputs (options, theory, modelling, troubleshooting, driver format)
  • Conventional Commit title (feat:, fix:, docs:, ...)
  • Commits are signed off (git commit -s) under the
    Developer Certificate of Origin

Seabed friction had no effect on the static solve: the friction springs
are anchored to the frictionless still-water layout, so a grounded run
on a slope with tan(theta) < mu, or laid with surplus length, still slid
or folded (an EI = 0 line on a 5 deg slope with mu = 1 folded 24 m past
its anchor, exactly as with mu = 0).

The new option staticsFriction asLaid follows OrcaFlex's "As laid"
policy: the line is assumed laid from its lower end along a lay azimuth
(default from anchor to fairlead, layAzimuth / layAzimuth<ID>) at an
as-laid tension (asLaidTension / asLaidTension<ID>, default 0), and
friction resists displacement from those positions in the static solve,
with the regularised law of the dynamics (isotropic and anisotropic).
The dynamics continue from the static friction anchors. Both line
families, the coupled aggregate and the C API share it.

With asLaid, the 5 deg EI = 0 line holds where it is laid (FairTen
714.2 -> 622.9 kN, friction within mu N at every grounded node, held
runs drift by 1.5e-10 of FairTen), and a 650 m finite-EI cable on a
10 deg slope, which failed, solves and holds. On a flat seabed laid at
its run tension the result equals the frictionless one (FairTen within
6e-6). As an illustration, the IEA-15 mixed example with asLaid has a
chain AnchTen of 368.2 kN instead of 1351.6 kN: friction holds back a
run laid slack and pulled taut.

The default is staticsFriction none, the previous behaviour and that
of MoorDyn, which is conservative for anchor loads; every example and
test deck is byte-identical under it.

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

- A finite-EI asLaid line whose lay azimuth leaves the vertical plane of
  the chord (e.g. 45 layAzimuth) was solved in that plane, because the
  3D requirement was set after the planar constraints were built, so a
  permanent lateral friction force remained (a held run drifted 1.2e-3).
  The requirement is now decided before the constraints; an azimuth in
  the plane (180) keeps the planar solve.
- The finite-EI reference is laid from the lower end, as on the EI = 0
  route, and only the geometric cross-plane offset of an in-plane line
  is zeroed, keeping the bathymetry sink offset (a cross-slope lateral
  anchor force of +269 N now -64 N against -59 N on the EI = 0 route).
- The fallback anchor walk and the planar-run diagnosis test for a real
  current, not for the friction carrier of a still-water asLaid line.
- asLaid is rejected by name on the multibody output and single-line
  routes that cannot apply it; an overflowing layAzimuth<ID> suffix
  names no LINE.
- The Python deck reader, writer and builder accept and validate
  staticsFriction, layAzimuth[<ID>] and asLaidTension[<ID>].
- Tests: off-plane and flipped azimuths, cross-slope, per-line
  precedence, anisotropic friction, a multi-section line, mobilised
  friction on the finite-EI slope, input rejection; Python tests.
  With the default option every example and test deck is
  byte-identical.

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

chatgpt-codex-connector Bot commented Oct 15, 2026 •

Copy link
Copy Markdown

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-10-16T06:45:14.344538Z 9750192 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 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: f69cd75312

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_Model.f90 Resolved
On a bathymetry whose slope varies, a positive asLaidTension turns at
every node of the laid path and presses the line into a crest or lifts
it from a hollow. The sink of the as-laid reference counted only the
node's weight, so a line laid at its as-laid tension did not rest at its
reference and friction was mobilised spuriously. The reference now adds
-T (t_out - t_in).n / k to each interior node's sink, evaluated on the
laid path before the sink, on the EI = 0 and the finite-EI routes. With
no laid tension the reference is bit-identical. A unit test on a crest
checks the correction against an independent evaluation.

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: 1f729383bf

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
layAzimuth<ID> and asLaidTension<ID> rows were range-checked only as the
final per-line value, so an invalid row (a negative tension, a NaN
azimuth) followed by a valid row for the same line passed silently.
The OPTIONS row check now applies the family rule (finite azimuth,
non-negative tension) to every suffixed row, as for the global rows and
as the Python reader does. Tests: shadowed negative tension and NaN
azimuth rows are rejected.

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: aa8846d862

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_Static.f90 Resolved
The laid tension's normal load P deepens a node's normal penetration by
P/k, which moves it horizontally by (P/k) grad(z)/s with
s = sqrt(1 + |grad z|^2); the sink, the factor of the gradient (w/k for
the weight), therefore gains P/(k s), not P/k. The correction now
carries the 1/s factor, taken from the node's own normal, and the unit
test and the theory page state it.

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: 1981277808

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_Static.f90 Resolved
A finite but huge asLaidTension stretched the laid elements without
limit, so the seabed path integration of the as-laid reference could
overflow its sub-step count or loop for billions of steps. A laid
tension above an element's EA (more than 100 % strain) now fails closed
with a named message, and a laid length beyond 1e7 m is refused, which
bounds the sub-step count. Test: a 1e30 N asLaidTension is rejected.

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: 16314565ad

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 src/CableDyn_HermiteCableStatic.f90 Resolved
The static-friction label marks a paragraph, not a section title, so
the bare :ref: references to it had no text and the Sphinx build (run
with warnings as errors) failed on four of them. Each reference now
carries its link text.

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

read-the-docs-community Bot commented Oct 16, 2026 •

Copy link
Copy Markdown

Documentation build overview

📚 CableDyn | 🛠️ Build #35185378 | 📁 Comparing 9750192 against latest (f27c5e3)

  🔍 Preview build  

17 files changed · ± 17 modified

± Modified

… drag

- The EI = 0 helper solve that seeds a finite-EI asLaid line did not
  mark its friction load as as-laid, so CD_Static_Line_Equilibrium
  tried the ordinary catenary/fold seeds instead of the laid-run seed;
  it now sets friction_as_laid.
- The finite-EI static solver ignored the carrier flag drag = .FALSE.:
  a friction-only current object with a nonzero velocity would still
  have loaded the line with drag and required drag properties. The
  element drag and its section properties are now zero for such a
  carrier, as on the EI = 0 route; the still-water carriers of the
  as-laid policy, which have zero velocity, are unaffected.

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: cc0436be0c

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 src/CableDyn_Static.f90 Resolved
… slope

- A finite-EI asLaid line with ATTACHMENTS on a bathymetry had its
  friction reference built from the smeared weights, while the
  attachment polish lumps each module's net weight at one node, so the
  normal sink showed up as a tangential deflection that mobilised
  friction. The reference is rebuilt on the final mesh from the lumped
  nodal loads (bare weight share plus the module's net weight) before
  the polish: on a 5 deg cross slope the kink at the module nodes falls
  from 4.65 mm to 0.16 mm and the held run stays at rest.
- The as-laid seed of a line whose last node lies below node 1 (lines
  without a Fixed End B) is now built on the reversed line from that
  grounded end and reversed back; it had fallen back to the suspended
  catenary seed.
- A finite-EI asLaid line over a bathymetry that slopes across its
  chord is solved in 3D, as with an off-plane lay azimuth; the planar
  solve kept the seed's lateral positions and the held run drifted.

Tests: att_cross (modules on a cross slope), case_as_laid_seed_from_last
(both numberings on a flat floor and a slope give mirrored equilibria),
and an at-rest march for the cross-slope cable. Default outputs are
byte-identical to dev.

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: 5de7b1765a

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
… fixes

- The as-laid friction reference was laid once on the deck mesh and
  interpolated onto refined meshes, so on a seabed curved along the
  line with a section change on the grounded run the refined solve
  differed from the same line declared on the fine mesh (0.95 mm, an
  8 N anchor tension change and a reversed lateral anchor force). The
  friction type now keeps the lay itself (origin, azimuth, tension,
  lower end, frame) and every static solve, and the dynamic hand-off,
  lays the reference on its own mesh with that mesh's lengths, EA,
  lumped weights and seabed stiffnesses (CD_HermiteCable_As_Laid_Offsets);
  the refined line now equals its fine-mesh twin to 1e-12 m.
- The finite-EI compatibility route (a line whose End B is not Fixed)
  ignored staticsFriction asLaid; it now refuses it by name.
- A still-water asLaid line keeps the tensile-polish fallback of a line
  without current, and its fixed-point and load-step failures name the
  friction instead of a current.
- A laid path longer than the cross-slope sample cap takes the 3D solve
  conservatively; the sample count is computed without integer
  overflow.
- Docs: the spring of a line laid on a slope carries the slope and
  turning load only (the normal sink adds no friction deflection); the
  none policy's anchors are described for still water and a current;
  the lay is from the lower end (the anchor, or the fairlead when that
  is lower); the asLaid rejection scope and its message are corrected.

Tests: a refined two-section line against its fine-mesh twin, the
compatibility-route rejection. Default outputs remain byte-identical.

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. Chef's kiss.

Reviewed commit: 9750192e40

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 b32d3f4 into dev Oct 16, 2026
15 checks passed
@SMI-Lab-Inha
SMI-Lab-Inha deleted the feat/static-friction branch October 16, 2026 08:09
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