Repository navigation
feat(outputs): equilibrium tension recovery, continuous touchdown, anchor uplift channels - #21
Conversation
…plift channels Finite-EI node tension, curvature and bend moment are recovered from nodal equilibrium. They had used the element-mean axial force EA(|r'| - 1), which oscillates between elements wherever the line bends over an element and exceeds the tension by EI kappa^2 on any mesh: on the 87-element lazy wave of the IEA-15 mixed example the interior node tension dropped to -173 N against a true 1.2 kN. Each element's end forces, with its own distributed loads, contact and inertia, now give the effective tension (the axial component of the section force, the force that balances the loads), the bend moment and the curvature as that moment over EI. The largest interior tension error against the converged equilibrium falls from 1552 N to 60 N on the example mesh and from 516 N to 0.3 N on a 1 m mesh. Line-end values, positions and the material-strain checks are unchanged. OutputRecovery element restores the previous definitions; the exact geometric curvature stays available as CD_HermiteCable_Dyn_Curvature_Exact and CD_HFMF_Curvature_Exact. The touchdown point is located inside the element by the parabola through the last grounded node and the next two, so it moves continuously instead of in steps of one element: under a surge the largest step between output rows falls from 4.64 m to 0.08 m with 5 m elements. Adds the anchor uplift channels AnchFz<L> and AnchFH<L> (vertical and horizontal components of the AnchTen<L> end force) and TDP<L>Grd (the grounded length) for the drag-anchor check, on every route. Range graphs and .t.out files written every step cost about 4 % more run time, plain channels under 2 %. The T-6 record of VALIDATION.md, which reads the static-profile curvature, moves from 0.056 % to 0.049 %. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
…y cache
- The recovered end moment of a held end laid on the seabed missed the
floor reaction of the end node's half element, so a laid anchor
reported a spurious bend moment (903 N m at the cable anchor of the
IEA-15 mixed example, 205 N m at the next node). The end element now
carries that reaction: 0.018 and 0.10 N m. Test in
tests/test_anchor_uplift.py.
- TDP<L>Grd was reset to 0 while only the end node was grounded and then
jumped by a full chord; it is now the deformed chord length from the
grounded end to the touchdown point throughout, and TDP<L>s +
TDP<L>Grd is the line length.
- The node recovery is cached per element on the state (t, q, v, a and
the load configuration) and reused across the Ten, Curv and BendMom
channels of an output row (150 channels: 0.61 s -> 0.55 s on a 64
element cable); outputs are bit-identical. Channel evaluation takes
the model INTENT(INOUT) (CD_AGG_EvalChannel and related).
- A section with EI below max(|w| l0^2)/12 times 1 m reports the exact
geometric curvature: the recovered moment carries an error
independent of EI that Curv = BendMom/EI amplifies (6.9 1/m against
0.12 1/m at EI = 100 N m^2).
- Regression tests pin the quadratic touchdown locator (Fortran and
Python). Docs state that end values are the end reactions while
interior values include inertia, that the recovery balance in
dynamics is the one at t_{n+1}, and that AnchFz is exactly 0 at a
grounded finite-EI anchor.
Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
…covery, O(n) node queries The OpenFAST CompMooring = 5 module no longer compiled: CD_AGG_ChannelHeader had become INTENT(INOUT) while CD_InitVars passes it part of an INTENT(IN) instance. CD_AGG_ChannelHeader and CD_AGG_GetInitLine write nothing and are INTENT(IN) again, as are the standalone driver's mixed-route header and initialisation printers; only the channel evaluator and the static profile, which reach the recovery cache, stay INTENT(INOUT), and every glue call of those passes the module-level instance or a local aggregate. The seabed force spread over the elements by the node recovery now matches the residual in a rounded bathymetry crease: it takes the crease curvature and adds the elastic increment of the penalty potential, as assemble_contact and the end force do, so interior tension, curvature and bend moment over a crease use the force the solve applied. A node query compared the whole line state with the cached one, so a loop over the nodes of a line (static profile, C API line values, a row of node channels) cost O(n^2). The cache is now keyed per element by its own 12 position, velocity and acceleration DOFs (the only state its end residual depends on) besides the time and the load configuration, so a query compares two elements and needs no list of the places that change the state. Tests: the pinned hang-off check of test_pinned_touchdown_stability and the kink checks of test_deck_hermite_cable read the geometric curvature (CD_HFMF_Curvature_Exact): the recovered curvature is zero at a pinned end by construction and is not a shape measure. test_anchor_uplift reads the anchor node and element length of the mixed example from its deck (the example is meshed with 248 elements since the rebase) and allows the bend of the laid run sinking into the penalty seabed beside the anchor. Documentation: the anchor uplift section no longer claims that AnchFz and TDP<L>Grd agree. AnchFz is the anchor reaction; on an EI = 0 line it holds the anchor node's lumped weight, so its sign change lags the lift-off of the anchor segment, and TDP<L>Grd (or AnchIncl) is the no-uplift check. The curvatures of the one-hour coupled full-turbine record, which cannot be re-run from the repository, are marked as the geometric definition; the Hs = 11 power-cable record and the OpenFAST tutorial give the recovered static values (Curv4N38 0.0902 1/m, BendMom4N38 1795 N m); the CHANGELOG qualifies the numbers measured on the example's former 87-element mesh and no longer says every other record is unchanged. Stale comments on the finite-EI segment tension and the TDP channel list are corrected. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
- The static-profile Tension column is described by its channel definition only; "the segment tension" was wrong for a finite-EI line, whose profile tension is the recovered nodal F.t. - test_anchor_uplift reads the bare type's diameter, mass per length and EI and the kBot option from the mixed example instead of hard-coding them, so the laid-anchor moment bound follows the deck. - The recovery-cache comment lists axial damping among the loads that advance the epoch, as Set_Axial_Damping does. 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: 939600106d
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".
The native aggregate builds every finite-EI line of a coupled deck (OpenFAST, FAST.Farm, the C API, the standalone mixed deck) held at a Fixed End B and refuses any other. The Python validator accepted such a line, for example a finite-EI cable shared by two turbines, together with its AnchFz and AnchFH channels, so a deck it reported valid failed at initialisation. It now refuses the line with the native message. An EI = 0 line shared by two turbines keeps its end-force channels. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
968f682 to
f9f2fd7
Compare
|
@codex review |
|
Codex Review: Didn't find any major issues. Swish! 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
Finite-EI line outputs that engineers read for design, node tension, curvature, bend moment and touchdown, were wrong or jumpy on practical meshes. They are now recovered from nodal equilibrium. The PR also adds the anchor uplift channels used for drag-anchor checks.
Equilibrium-recovered node values (default)
EA(|r'| − 1). That value oscillates between elements wherever the line bends over an element, and exceeds the tension byEI κ²on any mesh. On the 87-element lazy wave of the IEA-15 mixed example, the interior node tension dropped to −173 N against a true 1.2 kN.|w| l0² /12 × 1 mreports the exact geometric curvature, becauseBendMom/EIwould amplify the recovery error there.OutputRecovery elementrestores the 0.1.1 definitions. The exact geometric curvature stays available asCD_HermiteCable_Dyn_Curvature_ExactandCD_HFMF_Curvature_Exact..t.outfiles written every step cost about 4 % more run time; plain channels cost under 2 %.Continuous touchdown point
The touchdown point is located inside the element by the parabola through the last grounded node and the next two. It now moves continuously instead of in one-element steps: under a surge, the largest step between output rows falls from 4.64 m to 0.08 m with 5 m elements. The Fortran and Python locators agree.
Anchor uplift channels
AnchFz<L>/AnchFH<L>: the vertical (positive up) and horizontal components of theAnchTen<L>end force. They equalPoint<P>Fz/Point<P>FHfor an anchor that holds one line.TDP<L>Grd: the grounded length, continuous;TDP<L>s + TDP<L>Grdis the line length.TDP<L>Grd(orAnchIncl) as the no-uplift check. On an EI = 0 line,AnchFzholds the anchor node's lumped weight, so its sign change lags lift-off.Records
Curv4N380.0902 1/m andBendMom4N381795 N·m.Tests
tests/test_anchor_uplift.py: the uplift channels on every route, a laid-anchor bend moment bounded from the deck's own properties, and the AnchFz lag.pre-commit run --all-filesand the Sphinx build with-Wpass.Checklist
pre-commit run --all-filespassesctest --test-dir build --output-on-failurepassespython -m pytest tests python/testspasses (if Python or validation records changed)[Unreleased](heading added if missing) for user-visible changesdoc/updated for changed inputs, options, or outputsfeat:,fix:,docs:, ...)git commit -s) under theDeveloper Certificate of Origin