Repository navigation
fix(statics): the natural-level test of the object balance cannot cycle - #135
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. Bravo. 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". |
|
@codex review |
de189af to
72780a8
Compare
|
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". |
72780a8 to
0067394
Compare
|
@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". |
|
@codex review |
0067394 to
e2cd0f4
Compare
|
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". |
The static balance of Connect/Free points, bodies and rods accepts a trial step that raises the force residual when the Newton step from it is at most half the current one (a taut line swinging about its anchor, which every straight step overstretches by its sagitta). Near the slack/taut kink of a line the analytic Jacobian is nearly singular and the Newton step grows again; that resets the measure, and the iterates cycled: a massless Connect point between a near-vertical heavy chain and two wires on the seabed went 4e4 N -> 6e6 N -> 4e5 N -> 1.6e5 N -> 4e4 N and around, every four steps, until the solve failed with "static point equilibrium not found" from every seed, at the deck position, at three translations and at the balance itself. An independent solution with elastic catenaries on a frictionless seabed puts the balance 5.6 m above the seabed. Such a step is now accepted only when the new Newton step is also at most half the shortest Newton step of the phase so far. Steps that lower the residual are unchanged; every example gives the same output (one log digit of a 1e-5 N force component apart). The new point_static_cycle test solves the deck at four translations and on twice its mesh, within 1.5 m (deck mesh) and 0.5 m (refined) of the independent balance. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
The [Unreleased] entries of the open changes are added together in one change, so that they do not conflict with each other. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@codex review |
e2cd0f4 to
052600a
Compare
|
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". |
A Connect point between a near-vertical heavy chain and a wire lying nearly taut on the seabed failed the static solve from every seed (fuzz campaign case pointsys_07092).
The balance of objects accepts a trial step that grows the residual when the Newton step from the trial point is at most half the current one (a taut line swinging about its anchor). That test compared only against the previous step, so a long step at a slack/taut kink reset the measure and the iterates could cycle forever. The test is now
|dx_c| <= 0.5*min(|dx_n|, the shortest Newton step accepted in the phase), which cannot cycle.Check. An independent elastic-catenary balance on a frictionless seabed puts the equilibrium at (−46.28, −215.17, −385.52). CableDyn now converges to (−45.53, −215.82, −385.97) on the deck mesh and to (−46.03, −215.39, −385.64) on the 2× mesh.
Test.
point_static_cycle: four translations of the deck plus the 2× mesh. Its tolerance is 1.5 m on the coarse mesh, whose own discretisation offset is 1.09 m. CTest passes on both BLAS kernels; examples are identical apart from one round-off digit in a log line.