Repository navigation
feat: a finite-EI line may end on a Free point (a free cable end) - #159
Conversation
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>
|
@codex review |
Codex Review Summary: ✅ CompletedThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
There was a problem hiding this comment.
💡 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".
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>
|
@codex review |
There was a problem hiding this comment.
💡 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".
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>
|
@codex review |
There was a problem hiding this comment.
💡 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".
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>
|
@codex review |
|
Codex Review: Didn't find any major issues. Delightful! Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
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". |
Summary
A finite-EI line can now end on a
Freepoint. 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 aFreepoint 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:
CoupledorVesselpoint (a still hang-off is aCoupledpoint without motion);BODIES,RODSor otherConnect/Freepoint.What changes
Mass,Vol,CdAandCAact on the End B node as an end attachment: weight and buoyancy, added mass, fluid inertia, drag.releaseoption), so the run starts at the end's rest position.Point<P>p…channels read the line's End B node.The seed length is
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
Freepoint of a deck is not such an end (a clamped or buoyant end, a secondFreepoint, aConnectpoint), 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
Freepoint. The Python deck reader takes the same rule.Checks
tests/test_free_end_deck.f90uses 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).As EI falls, the end position in current converges to the EI = 0 result:
python/tests/test_deck_native_parity.py::test_free_cable_end_matches_the_driverchecks that the Python reader and the native driver agree on the two accepted and three refused decks.Gates
-fchecksubsetsphinx-build -WTwo 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 newreleaseargument defaults to false.