Repository navigation
fix(statics): solve light slack finite-EI lines; keep a line's azimuth continuous - #59
Conversation
…h continuous A finite-EI line longer than its span with no net weight, or too little for its bending stiffness, failed its static solve. With no catenary to start from, both routes reached the compressed straight strut (a saddle) or stalled at the round-off of the axial forces, EA eps |r|/h, which a weightless line's unit force scale puts above the tolerance (0.001 N/m on a 120 m line with EI 1e4 failed; 0.01 N/m passed). When both routes fail on a slack, planar line in still water with |w| < 100 EI/L^3, the line is now solved with that auxiliary weight (of the sign of its net weight, downward for a weightless line) and carried back to its own weight by a continuation in the weight, held in the vertical plane of its chord and accepting the round-off floor of the axial forces; the result is audited and stability-checked as the routes' are. A weightless line bows as the pinned-pinned elastica: end thrust 7.0563 N and mid-span bow 17.9399 m against 7.0564 N and 17.9399 m exact. Nothing in the deck chooses the side of its bow, so it is solved bowed downward and a note says so; with its ends one above the other it is still refused, now by that cause. The tangent azimuth of a line along +X jumped between 0 and about 360 from one output row to the next as the line swayed a fraction of a degree to either side, or by the sign of a round-off component: on the IEA-15 mixed OpenFAST deck 315 to 485 of 801 rows of each cable azimuth channel read 359.9x. A line whose static chord heads within 45 deg of +X now reports its azimuths in (-180, 180], every other line in [0, 360) as before, so the cut of a line's range lies at least 45 deg from its heading; a round-off component across the cut reads on its included side. 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: e38ff8a776
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".
…htless-bow note The recursive builds of a finite-EI line (weight continuation, coarse current pass, still-water references) ran without the standalone controls, so they refused a Fixed End A that the standalone build of the same line admits; the weight continuation of a weightless line with both ends Fixed (legal in a deck with dynamic points) failed on it. They now inherit the outer build's allowance (fixed_fairlead). All 52 examples are unchanged. The weightless-bow note was reported before the build cleared its note buffer, so the coupled aggregate, which prints nothing itself, never received it. It is now reported with the other initialisation notes. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@codex review |
|
Codex Review: Didn't find any major issues. Keep them coming! 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". |
Two items from the robustness backlog.
1. Light slack finite-EI lines
A finite-EI line longer than its span with no net weight, or too little for its bending stiffness, failed its static solve.
Cause. With no catenary to start from, both routes ended in one of two ways:
On a 120 m line with EI = 1e4 N·m², a net weight of 0.01 N/m passed and 0.001 N/m failed.
Fix: a weight-continuation route, run only when both routes have failed (
light_line_route).tensile_safety, and with |w| < 100·EI/L³.Recursive builds. The weight continuation, the coarse current pass and the still-water references now inherit the outer build's allowance for a Fixed End A (
fixed_fairlead). Before, they ran without the standalone controls and refused it.Weightless line. It is the pinned-pinned elastica. Nothing in the deck chooses the side of the bow, so it is solved bowed downward (the limit of a vanishing weight) and a note says so. The note is printed by a standalone run and returned to the coupled aggregate. With its ends one above the other it is still refused, and the message now names that cause.
Results (120 m pinned line, ends 113 m apart):
2. Azimuth range
The tangent azimuth of a line along +X jumped between 0 and about 360 from one output row to the next as the line swayed a fraction of a degree either side of 0. The sign of a round-off component did the same. On the IEA-15 mixed OpenFAST deck, 315 to 485 of the 801 rows of each cable azimuth channel read 359.9x.
Fix. A line whose static chord heads within 45° of +X now reports its azimuths in (−180, 180]. Every other line keeps [0, 360).
Implementation.
DeckLine%azi_signed) and carried onto the EI = 0 model and the cable.Checks
light_slack_staticstest against the exact elastica;driver_channelsazimuth cases;driver_msg_weightless_finite_ei(now solves, with the note) and_vertical(refused by name);light_slack_staticswith both ends Fixed, andflagship_compression_notechecking that the aggregate receives the weightless-bow note (it fails without the fix).test_long_failure_message_is_kept_wholeneeded a new message source: the weightless deck it used now solves, and no other deck's message is longer than 1024 characters. It now uses a missing deck at a 1,100-character path, a 1,319-character message.-W, and fprettify is clean on the changed lines.