Repository navigation
fix: static equilibria over non-planar bathymetry - #16
Conversation
A finite-EI line over any structured bathymetry that is not a plane along its chord failed its static solve, even with 2 cm roughness: 39 of 192 runs of a rough-seabed sweep failed, most of them on a 25 m survey grid. The catenary seed is laid on the plane fitted along the chord and was rejected as soon as a node sat more than about 1e-6 (L + |z|) below the real bed; on a non-planar bed the anchor walk was not allowed, and the mesh-sequenced fallback ended on a kinked branch. Over a non-planar bathymetry the seed nodes deeper below the real bed than their static penalty penetration (nodal weight over kBot Diam length) are now draped onto the bed instead of rejecting the seed, and the bending-stiffness continuation, which queries the full surface, settles the contact. The anchor walk also runs there, with the walked anchor kept at its height above the bed under it; its failure no longer marks the deck inadmissible, so the mesh-sequenced route still runs. Planar beds keep the old checks exactly, and the final equilibrium is audited, stability-tested and kink-checked as before. Rough-seabed sweep, finite-EI: 153/192 -> 192/192; long lines walked into place on rough beds: 0/5 -> 5/5 (FairTen within 0.02 % of the flat-bed walk); converged twins on a 4x mesh agree within 1 %. Decks that already solved on a rough bed and now take the primary route change by at most 0.03 % in FairTen and 2.2 % in AnchTen (0.5 m roughness, where the deck and 4x meshes differ by up to 13 %). All examples and driver test decks are byte-identical. New statics-matrix decks ROUGH_1001-1003 with mesh twins fail on the base and pass. EI = 0 lines resting in a crease of the bilinear bed (a trench bottom, a valley of a 2D grid) still fail: the contact normal jumps across a grid line, so the discrete problem has no equilibrium there. The troubleshooting page documents it. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
The bilinear bathymetry surface has a slope jump across every interior grid line. A node resting in a concave crease (a trench bottom, a valley of a 2D survey grid) took one cell's normal, so its contact force always pointed back across the crease and the discrete problem had no equilibrium there: EI = 0 lines whose slack length piles in a trench failed their static solve for trench depths of 20-26 and 30 m, and 3 of 4 lines on a +-0.5 m 2D random grid failed. Each interior grid line is now rounded within a band of 5 % of the smaller adjacent spacing by the C2 fillet h(u) = (delta - |u|)^3 / (6 delta^2) times the slope jump, as a tensor product across both directions, so height, gradient and curvature are continuous; valleys stay convex. The surface moves by at most |J| delta / 6 (1.7 cm for a 0.2 slope jump on a 10 m grid). A crease that would move the surface by less than 1 um is not rounded, so planar grids stay bilinear bit for bit. Inside a band the contact force is the gradient of the penalty potential with its consistent tangent, in the statics and the dynamics of both line families, the friction anchors, end forces and outputs; Python's cabledyn.Bathymetry mirrors the surface to 1.4e-14. A Fixed anchor at the tabulated depth of a creased grid node is placed on the rounded surface. Trench-depth sweep 5/11 -> 11/11, EI = 0 rough sweep 191/192 -> 192/192, bathymetry families 52/75 -> 65/75. In a trench the slack pile gives AnchTen 73.15 kN against w dz = 73.24 kN. Previously converged rough-bed decks change by at most 0.04 % in FairTen (0.40 % for one deck settling in another valley) and up to 8.5 % in AnchTen, from removing the spurious horizontal reaction of one-sided normals; the deck-to-4x-mesh AnchTen spread on 2D rough beds roughly halves. All examples and driver test decks are byte-identical. A rejected anchor walk over a non-planar bed no longer claims the line is too long for its span. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
- The anchor walk over a non-planar bathymetry moved the anchor on the straight line between its start and the deck anchor, which a ridge or dip between them could put below or far above the bed. The walked anchor now keeps its height above the bed under it at every step, as documented, and the predictor starts from the current anchor. - crease_blend read an uninitialised flag when the second row of an x band had no crease. - The docs and comments now state the rounding bound per line (the roundings of two lines add at a crossing), that only an exactly planar grid stays bilinear bit for bit, that the friction capacity uses the normal force without the in-band curvature term, and that the energy agrees with the force up to the bilinear twist; the walk failure no longer asserts the line is too long. - The C2 test checks z_xy against finite differences. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
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: b802b9f4f2
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".
A Fixed point in a crease was accepted anywhere between the rounded seabed and the bilinear grid surface and moved onto the rounded one, so an anchor well below the actual seabed but above the grid surface was silently lifted. It is now accepted only within the seabed tolerance of either surface: at the tabulated depth it rests on the seabed and is placed on the rounded surface; between the two but near neither it is judged by its distance to the rounded seabed alone. New driver tests on a V valley: an anchor at the tabulated depth initialises, one 1 cm below the rounded floor is rejected. 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: c5c71c219c
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".
Inside a crease band the EI = 0 static residual and its friction anchors took the friction capacity from the norm of the band contact force, which includes the curvature term of the penalty potential, while the Hermite statics and the dynamics use the scalar normal law at the normal penetration. Both EI = 0 sites now use the scalar law in a band, so the capacity is the same across routes and at the dynamic hand-off; outside the bands the computation is unchanged. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@codex review |
|
Codex Review: Didn't find any major issues. 🚀 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
Static equilibria over real (non-planar) bathymetry. A statics robustness campaign (352 decks plus a 384-run rough-seabed sweep) found two failures that every survey bathymetry can trigger.
1. Finite-EI lines over a non-planar bathymetry failed, even with 2 cm roughness (39 of 192 sweep runs; mostly on a 25 m survey grid).
2. EI = 0 lines resting in a crease of the bilinear bed failed (a trench bottom, a valley of a 2D grid).
J (δ − |u|)³ / (6 δ²)of the slope jumpJ, as a tensor product, so height, gradient and curvature are continuous and valleys stay convex.|J| δ / 6along one line (1.7 cm for a 0.2 slope jump on a 10 m grid). At a crossing the two roundings add.Bathymetry.Fixedpoint at the tabulated depth of a creased node is placed on the rounded surface.Results
Tests
cable_statics_matrix:ROUGH_1001–1003with mesh twins, all failing on the base.test_bathymetry.f90:test_statics_robustness.py: an independent re-implementation of the rounded surface with a nodal balance, plus the trench and 2D-rough decks, all failing on the base.python/tests/test_clearance.py: fillet values, continuity, planar exactness.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)[Unreleased](heading added if missing) for user-visible changesdoc/updated for changed inputs, options, or outputs (theory, file formats, troubleshooting, Python post-processing)feat:,fix:,docs:, ...)git commit -s) under theDeveloper Certificate of Origin