Repository navigation
feat(dynamics): sub-step EI = 0 steps that turn or snap taut - #25
Merged
Merged
Conversation
At dtM 0.1 s a taut segment of the Lozon 80 m all-chain mooring turns by up to 6 deg per step in 5 m / 7 s heave, and both generalised-alpha blends gave snap-load peaks 10 to 20 % low. The release cap was not the cause: it acts in 0.3 % of the element steps, never near a peak, and the cycle maxima with and without it agree to within 1 %. The peaks followed the algorithmic damping, so a coarse step under-resolves them whatever the blend. CD_Step_Model now measures each converged step against its committed start. When a segment that ends the step taut turned by more than ei0_substep_angle (default 1 deg), or a segment slack at the start ends above a quarter of the largest step-start tension, the interval is solved again from the same committed state in max(4, ceil(turn/angle)) equal sub-steps, at most ei0_substep_max (default 16). The end motion follows the quintic of the recovering step and the last sub-step lands on the given end state. The sub-stepped interval is measured once more and re-solved when its turn needs more sub-steps; a sub-step that fails returns the plain step. The decision depends only on the committed state and the step inputs, so a restart repeats it. Every route that steps EI = 0 lines goes through it (standalone lines and line systems, OpenFAST, FAST.Farm, the C API) except the monolithic junction coupling, which needs the nominal step's end reaction and tangent. The recovering step keeps taking its rungs as given. New OPTIONS ei0_substeps auto|off (default auto; off with False alpha_force_blend unless the deck sets it, so paper mode is unchanged), ei0_substep_angle and ei0_substep_max, mirrored in the Python deck reader. off gives the previous results bit for bit. The run audit measures turns and axial-wave crossings per solver step, reports the sub-stepped steps, and its turn note states the peak underestimate. Over seven runs with amplitudes 3e-4 apart, against 0.5 / 0.25 ms runs, the 80 m heave fairlead and anchor maxima move from 15 / 17 % low to 4 / 8 % low, and the 200 m semitaut anchor maxima in 10 m / 14 s and 5 m / 7 s surge from +16 / +26 % to -1.4 / -2.6 %. 19 of 21 EI = 0 dynamic examples are unchanged; the line-break decks' pre-failure snap moves by 5-11 %. Bergdahl RMSE 1.58 -> 1.59 N (record files and provenance updated); the other validation records move within their recorded ranges or not at all. The 20-run mooring envelope takes 1.65 times as long. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
The halves of a line-system step that CD_Step_System halved after a failure now take their steps as given (CD_Step_Model as_given), as the rungs of the recovering step do, and the system rollback restores the run audit's largest solver step with the line state. A step whose sub-step fails now keeps the plain step's own converged result instead of solving it a third time. The turn trigger counts a segment that ends the step above 1e-3 of the largest step-start tension, the audit's floor. Counting only segments taut at both ends, as the review suggested, left the Lozon semitaut anchor peaks 5 % high on average and up to 25 % high in single runs, so the trigger keeps segments that were slack at the step start. The strains use the step's own unstretched lengths, and a comment marks where a length that changes within the step would need its step-start value. The counts are visible on every route: OpenFAST and FAST.Farm print them at the end of the run, CD_AGG_Get_Substep_Counts and CD_Get_System_Substep_Counts return them, and the standalone driver notes once per run that the monolithic body/point step is not sub-stepped. Tests cover the snap-only trigger, the re-measure path, the failing sub-step fallback (equal to off bit for bit), the ei0_substep_max cap, and the complete restore of the viscoelastic, Syrope and seabed friction states, through test-only hooks. The slack-dynamics bounds are widened around the measured peaks. Figures with the final build: the 80 m heave maxima are 3.8 / 7.7 % low, the 200 m semitaut anchor maxima 1.4 / 2.6 % low and the 80 m surge maxima 1.8 % low / 1.4 % high, over seven runs. The Bergdahl records, the L2-2 parity and the shipped examples match the previous commit. The 20-run mooring envelope takes 1.63 times as long (1.6 to 2.5 times on the 5 m / 7 s and 10 m / 14 s motions, 4 to 7 sub-steps). The docs, CHANGELOG, VALIDATION and ARCHITECTURE now give these figures. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
A convergence study of the light-cable and stiff-seabed reproducers of the force-blend fix shows that the undamped EI = 0 deck has no converged snap peak: the peak rises as dtM falls (0.32 to 0.46 MN at microsecond steps, also with an explicit lumped-mass solver), as single segments rattle, and falls with mesh refinement at a fixed step. Its 20 ms averages converge to 0.083 / 0.047 MN, and converged finite-EI runs give 0.093 MN at the fairlead and 0.057 MN at the anchor. On the stiff seabed the EI = 0 peak does not converge either. The CHANGELOG, theory and options pages no longer call the light-cable or stiff-seabed figures references; they give the finite-EI values instead of "0.1 to 0.18 MN at rhoInf = 0 and with a finite-EI model". The sub-stepping entry states that on this undamped cable the sub-steps resolve more of the segment rattle and can raise isolated spikes (anchor 0.16 to 0.52 MN at dtM 0.5 ms), and that with physical axial damping they change nothing. The modelling guide and the snap-note entry of the troubleshooting page now advise physical axial damping (BA in N s, not the per-segment damping-ratio form, which changes with the mesh) or finite EI to obtain converged snap peaks. The slack-dynamics test header says the same of its bounds, which catch a spike or a lost snap rather than a reference. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
…t only committed steps The depth-floor rerun of a stalled line-system step now steps every line as the nominal step does, sub-steps included, so its result is again that of the step without the fallback; only the halves of a recovery take their steps as given. The monolithic junction arms the end query only on lines with an active junction DOF, so a line whose ends are all fixed or anchored is sub-stepped there too. The docs and changelog state that the monolithic scheme is the default of standalone decks with bodies, rods or free points, that the lines attached to them are not sub-stepped (7 of the 21 shipped EI = 0 dynamic examples), and what a triggering step costs at most. The trigger takes the segment tensions the run audit takes (the viscoelastic and Syrope law tensions included), floors the step-start tension scale at 0.1 % of the line's initial tension, and treats a slack-to-taut snap as one only when the step does not resolve the axial wave over the segment. The Bergdahl matrix at 0.3125 ms therefore takes no sub-step and is back to its previous record bit for bit; its 0.1 m mesh and 0.625 ms runs keep theirs. The light cable at 0.5 ms takes no sub-step either. Flooring at the full initial tension was tried and left the Lozon semitaut anchor peaks up to 29 % high, so the floor is 0.1 %. The sub-step diagnostics are 64-bit, roll back with the line states (line system rollback, the fallback frame, the system snapshot and the stall recovery) and are reported as steps examined. The ei0 settings are checked when the model is initialised, and the deck parser applies the Python reader's rule to ei0_substep_max. The sub-step slots and the recovery snapshot share one copy routine of the committed state. The OpenMP line loop is scheduled dynamically; results do not depend on the thread count. Tests: a partly taut snap case on each side of the quarter threshold, a case whose step resolves the axial wave, init-time rejection of invalid settings, deck rejection of bad ei0 options, the viscoelastic anchor bound checked against the uncapped figure with every step taken as given, and a sway turn bound relative to the unresolved turn. Figures in the docs, the changelog, VALIDATION.md and the Bergdahl record are updated from reruns. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
The release cap of the force-blended EI = 0 step skipped every segment slack at the step start. A damped segment whose ends separate there still keeps alpha_f T_d,n of its step-start dashpot force along its old chord, and returns alpha_f T_d,n p to the motion when the step turns or reverses its ends, with no strain energy behind it. The kept share of such a segment now has the dashpot's own one-step dissipation as its budget, W_d = T_d,n |ldot_n| dt, ldot_n the dashpot's elongation rate at t_n (the axial rate, less l_n l0_dot/l0 while the line pays out, so W_d > 0 whenever T_d,n /= 0). When p > 0 the kept force alpha_f T_d,n is replaced by (W_d + N_d)/p when that is smaller, with the end share's credit N_d = max((1 - alpha_f) T_d,n+1 p_n+1, 0); a compressive T_d,n is capped alike for p < 0. The kept dashpot share of an element slack at the step start then returns at most its own one-step dissipation plus the end share's credit. The capped force grows without bound as p -> 0, so it is continuous there, and alpha_f |p| <= |ldot_n| dt is a sufficient test of an inactive cap. The tangent takes dp/dd = -t_n and, while the credit is positive, the dependence of T_d,n+1 and p_n+1 on q_n+1 (through v_n+1) on the banded, dense and probe paths. Taut-start and undamped segments are unchanged. In the test chain (a segment slack at t_n moving at 0.05 to 2 m/s, either sense, turning by 0 to 180 degrees) the kept share returned up to 45.6 times W_d + N_d (44.6 W_d above the bound) before; with the cap it stays within the bound to 8e-14 W_d on the 29 of 448 rows where it acts, a segment with no step-start dashpot force keeps the plain blend bit for bit, and the tangent of capped rows matches the finite difference to 1.2e-10 on both paths. Of the 52 shipped examples 50 are byte-identical. The two Volturnus line break decks (chain with zeta damping in a JONSWAP sea) diverge from t = 246 s pointwise, as slack segments do, while their tension peaks change by at most 0.01 %, means by at most 0.02 % and standard deviations by at most 0.04 %. The light-cable, viscoelastic and Syrope reproducer bounds still hold. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
Owner
Author
|
@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. |
|
Codex Review: Didn't find any major issues. You're on a roll. 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". |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
At typical coarse steps, the snap peaks of tension-only (EI = 0) lines were set by the time step rather than by the physics, under any scheme. Segments rotating several degrees per step left all-chain snap peaks 10–20 % low, and semitaut peaks came out high. This PR re-solves such steps in sub-steps, by default.
Trigger. After a line step converges, it is re-solved from the same committed state in sub-steps along the existing quintic end-motion boundary when either:
ei0_substep_angle(default 1°; n = max(4, ⌈turn/angle⌉), capped byei0_substep_max, default 16); orThe result is re-measured once. If a sub-step fails, the plain step is kept. Stall-recovery rungs are taken as given.
Options.
ei0_substeps auto|off;offreproduces the previous results bit for bit.False alpha_force_blend(paper mode) turns it off unless the deck sets it.Routes. Covered: standalone, line systems, the staggered multibody march, OpenFAST, FAST.Farm and the C API. Lines with an active junction DOF in the monolithic body scheme are not sub-stepped (they need the plain step's end tangent). The monolithic scheme is the default for decks with Rigid6 bodies, rods or Free/Connect points; their junction lines are not sub-stepped, and the run says so.
Reporting. The run audit measures per solver step. OpenFAST prints the sub-step counts at the end of the run.
Start-slack dashpot share bounded. A segment slack at the step start that carries a step-start dashpot force now has its kept share bounded too. It may return at most its own one-step dissipation T_d,n·|l̇_n|·Δt, plus the end share's credit. The bound is continuous at the reversal and has a consistent tangent. Before, a turning or reversing step returned up to 45.6 times that bound. 50 of 52 examples are byte-identical; the two line-break decks move by at most 0.04 % in their tension statistics.
Snap-load documentation corrected. The undamped EI = 0 light-cable reproducer from the force-blend change has no converged snap peak: the peak rises as dtM falls, as single segments rattle, and an explicit lumped-mass solver agrees. Converged finite-EI runs give 0.093 MN at the fairlead and 0.057 MN at the anchor. The CHANGELOG, theory and modelling guide say so, and recommend physical axial damping or finite EI for converged peaks.
Results
Lozon moorings at dtM = 0.1 s, mean of 7 runs, against 0.5 / 0.25 ms references:
Tests
offbit for bit), the cap, and restore of viscoelastic, Syrope and friction state.pre-commit run --all-filesand the Sphinx build with-Wpass. OpenFAST builds, and its smoke and restart runs pass.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