Repository navigation
fix(statics): refine a graded mesh element by element to the bending length - #125
Conversation
|
@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. |
|
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". |
…length A finite-EI static route that fails on a deck mesh with elements longer than half the bending length (EI/|w|)^(1/3) is repeated on a refined mesh. That mesh was the whole line refined uniformly by the factor of its worst element, which keeps a graded deck's ratios and refines its short elements with the long ones. A lazy wave meshed 4 m at its sag bend, 0.9 m over its buoyant section and 10 m at its touchdown (half its bending length is 2.5 m) failed in an oblique or cross current: the routes stopped on the deck mesh, the 8x refined mesh stalled at the start of its stiffness continuation, and the deck reported "the line is already in axial compression without the current", although the same layout solves on 2 m elements. That compression (-2.8 kN element mean where the line carries about +1 kN) is the long elements' axial oscillation beside the short ones. When the uniform refinement fails too, the route is now repeated on the deck mesh with each element split only into the power of two (at most 16) that brings it to half the bending length. The six failing decks of a sweep over current speed, heading, module count and refinement now solve without a fallback, within 1.2e-3 of their fairlead tension of the same decks on 2 m elements; a grading sweep (buoyant section refined 1, 2, 4 and 8 times in four currents) converges throughout. Decks that solved before are unchanged, except two that had failed their uniform refinement and solved on the deck mesh by a later route: they now solve on the mesh refined to the bending length, closer to a fourfold refined reference (1.3e-3 and 3.8e-4 against 2.7e-3). The still-water compression diagnosis of a failed solve in a current now names a compression read on elements longer than half the bending length as possibly the mesh's, with the remedy, instead of declaring that no equilibrium exists. New test graded_mesh_statics: the six decks, two grading ratios that solved before, and two comparisons with the 2 m mesh. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@codex review |
8c958b2 to
eaea3c9
Compare
|
Codex Review: Didn't find any major issues. Nice work! 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". |
Six frictional lazy-wave decks with a strongly graded mesh failed their static solve in a 45° or 90° cross current. The mesh had 4 m elements at the sag bend next to a 0.9–1 m buoyant section, and 10 m elements at touchdown. The solver reported "no static equilibrium", yet the same decks solve on 2 m elements.
Cause
The refinement strategy. Half the bending length, (EI/|w|)^(1/3), is 2.5 m there, so both long sections break the resolution rule.
refined_restartrefined every element by the worst element's factor (8×), which keeps the 11:1 grading. That mesh stalls too.Fix
rule_restart. It runs whenuniform_restart(the formerrefined_restart, unchanged) fails. It repeats the route on the deck mesh, splitting each element into the power of two (at most 16) that brings it to half the bending length and leaving the others alone.No tolerance or deck-syntax change.
Evidence
Tests
graded_mesh_statics: the six failing decks, grading controls and two 2 m-mesh comparisons. It fails on all six before this change (exit 2) and passes after it, in 37 s Release and 194 s Debug.