Repository navigation
fix: carry the end weight moment at an anchor resting on the seabed - #14
Conversation
A one-hour coupled OpenFAST run of the IEA-15 MW mixed deck showed the power cable's anchor tension jump from 1.22 kN to 3.1 kN about 25 s in and stay there while the platform drifted toward the anchor; without seabed friction it declined to 0.6 kN. The friction law is not at fault. The seabed contact acts at the nodes, which carry no moment, so at a held anchor end resting on the floor the consistent end moment of the end element's weight (w L^2 / 12) had nothing to react it: the free end tangent turned 1.9 deg into the floor, the element dipped 27 mm below the seabed between its nodes, and membrane locking put -47 kN to +127 kN of axial force in it about a 1.2 kN line tension. The compressed part buckles sideways once the hang-off sways; the bowing element pulls its neighbours toward the anchor and friction locks them there. Without friction the end nodes wandered by up to 0.18 m. The seabed now carries the end element's weight moment at a held line end resting on the floor, along the floor normal on a slope, in the statics and the dynamics (a constant load; the tangent is unchanged). The static near-anchor tension is uniform (1218.204 N) and the anchor curvature drops from 1.5e-2 to 9e-7 1/m; the coupled anchor tension stays at 1.22-1.38 kN. Lines whose held end is off the floor are byte-identical; the shipped finite-EI examples with a grounded anchor change by at most 0.7 N. A regression test sways the hang-off of that cable for 30 s. Two decks of the statics matrix change outcome, with the evidence in the matrix: LW_1015__cur_fr fails closed (its old hairpin is reachable only through compression, which its tension-only deck rules out), and CUR_1013 now finds the equilibrium with the grounded run turned sideways, because a refinement stopped on compression in a current now names the current limit and the driver retries out of the plane. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
The coupled finite-EI touchdown record rested on a 20 s aggregate trajectory and said it was not a full-turbine DLC. A one-hour run of the IEA-15 MW mixed model (normal turbulence at 10.6 m/s, JONSWAP Hs 8 m, AeroDyn with the rotor held, a SeaState grid covering the lines) completes without recoveries; the hang-off tension, grounded length and mesh-converged hog curvature are recorded, with the touchdown curvature that the deck's 10 m laid elements under-resolve, and the chain-only twin matches stock MoorDyn to 0.3 %. With the anchor-end correction the laid cable's anchor tension stays at a median of 1.39 kN with sub-second stick-slip peaks; before it, it locked at about 2.75 kN. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@codex review |
Codex Review SummaryThis 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: 63c130f129
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 found that the floor carried the end element's weight moment whenever the held end node touched the seabed, so a taut line anchored on the floor whose first element rises into the water lost the end moment of that element's weight: the floor does not support it. The support now also needs the element to lie on the floor: it is scaled by a C1 smoothstep S(r) of r = N_in / (w l0 / 2), the elastic normal force of the element's inner node from the contact law the assembly uses over its half share of the element weight. A laid element (r about 2) keeps the full support; an element whose inner node is clear of the floor gets none, and its line is bit-identical to the same line without a seabed; in between the term is smooth and its tangent is assembled in the statics and the dynamics. A test checks the taut line anchored on the floor against the line without a seabed, statics and held dynamic steps, bit for bit. The slope-polish test of hermite_cable_static failed on Linux: its layout touched down at a node with neighbouring equilibria 3 cm apart, and under some BLAS kernels even its reference state was unstable. The fairlead now sits at x = 200 m, where every kernel reaches the same stable reference, every clear node stands 0.3 m above the floor, and both polishes return to it from four times the perturbation the test uses (default, Prescott, Haswell and SkylakeX kernels; Release and Debug). The shipped finite-EI examples with a grounded anchor now change by at most 0.34 N from dev. 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: c747e7e357
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 found that inside the transition of the end support (0 < S < 1) the energy-minimisation potential varied with the inner node through S, while the residual carries the support load only on the end tangent, so the potential was not a potential of the residual and the Armijo test compared R.dq with the derivative of a different function. Each energy line search now holds the share S0 of its starting point; with S fixed, the gradient of the support energy is exactly the residual's support load at every trial point. The hold is released when a step is accepted or the search stalls, and the torsion descent, which compares energies the same way, holds it too. The alternative, a conjugate force on the inner node (about 0.9 MN here), is a contact force the floor does not exert and would have changed every equilibrium and the dynamics; the support load stays non-conservative like current drag. A new check compares central differences of the held-share potential with R.d along four directions with the inner node mid touchdown (agreement 1e-5; with the share free the inner-node term is off by 8.9e5). Every example output is unchanged. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@codex review |
|
Codex Review: Didn't find any major issues. Hooray! 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
Fixes a spurious, permanent rise of the anchor tension of a finite-EI cable laid on the seabed, found in a one-hour full-turbine OpenFAST run, and records that run.
Symptom. In the IEA-15 MW mixed model (
examples/iea15mw_umaine_mixed_cabledyn.dat, a lazy-wave power cable with about 38 grounded nodes,frictionMu 0.35), the cable'sAnchTen4jumped from its static 1.22 kN to about 3.1 kN some 25 s into the run and stayed there for the whole hour, while the platform drifted 22 m toward the anchor and the line slackened. Without friction it declined smoothly to 0.6 kN.Cause (not the friction law). The seabed contact acts at the nodes, which carry no moment. At a held anchor end resting on the floor, the consistent end moment of the end element's weight (
w L² / 12) had nothing to react it:The friction model itself is correct: its force opposes slip, its return mapping only dissipates, and its anchors are saved and restored correctly.
Fix. The seabed now carries the end element's weight moment at a held line end resting on the floor, along the floor normal on a slope, in the statics and the dynamics. After review, the support also needs the end element itself to lie on the floor. It is scaled by a C1 smoothstep of the inner node's elastic normal force over its half share of the element weight. A laid element keeps the full support, and an element rising from an anchor on the floor gets none, which leaves the old result bit for bit. The static near-anchor tension is uniform (1218.204 N), and the anchor curvature drops from 1.5e-2 to 9e-7 1/m.
Results
AnchTen4median (static 1.22 kN)AnchTen4excursionsFairTen4Example decks.
EI = 0, rod and body decks), andlaid_cable_cross_current.mixed_body_rods_pointsFairTen8).Statics robustness matrix. Two entries change outcome; the evidence is recorded in the matrix:
LW_1015__cur_fr(1 m/s current, friction) now fails closed. Its old "admissible" state was a hairpin past the anchor that the old code reached only through the mesh-sequenced fallback at its exact seabed stiffness (±0.001 % ofkBotfailed). A slow dynamic current ramp reaches the hairpin only by passing through compression, which this tension-only deck rules out. Withtensile_safetyit stops at 0.37 m/s, as the static solve does.CUR_1013(1.9 m/s current, no friction) used to fail closed and now finds an equilibrium with the grounded run turned sideways on the seabed. When the refinement of the catenary continuation stops on compression in a current, its failure now names the current limit, so the driver retries out of the plane. Patched with this one change, the old code finds the identical state.Full-turbine touchdown record (VALIDATION.md, coupled finite-EI touchdown row): the cable gap on the coupled route was "never a full-turbine touchdown DLC".
Tests
case_grounded_anchor_end(deck_hermite_cable): the power cable with 2 m of hang-off sway for 30 s. Before the fix the anchor tension goes 1218 → 3775 N and the anchor tangent dips (share 3.2e-2), so the test fails; after the fix it passes.check_taut_line_anchored_on_floor: a taut line anchored on the floor whose first element rises is bit-identical to the same line without a seabed, in statics and held dynamic steps. Against the first version of this PR it fails three assertions (a 7 mm move, anchor curvature 2.9e-3 to 4.3e-3 1/m).hermite_cable_staticslope polish: the old layout (fairlead at x = 150 m) touched down at a node, with neighbouring equilibria 3 cm apart, and failed on Linux. The fairlead now sits at x = 200 m. Every BLAS kernel reaches the same stable reference, and both backtracking polishes return to it from four times the perturbation the test uses (default, Prescott, Haswell and SkylakeX kernels; Release and Debug).cable_statics_matrix: updated expectations as above, each with awhyfield.pre-commit run --all-filespasses.Checklist
pre-commit run --all-filespassesctest --test-dir build --output-on-failurepassespython -m pytest tests python/testspasses (if Python or validation records changed) — the statics matrix harness ran in the suite[Unreleased](heading added if missing) for user-visible changesdoc/updated for changed inputs, options, or outputs (theory: the end support)feat:,fix:,docs:, ...)git commit -s) under theDeveloper Certificate of Origin