Repository navigation
feat: amplitude-dependent VIV coefficients (VIV AMPLITUDE section) - #155
Conversation
Thorsen, Saevik and Larsen (J. Fluids Struct. 61, 2016) make the cross-flow excitation coefficient of the synchronisation model a function of the vibration amplitude, C_v(y0/D), fitted to riser tests; drag amplification laws of vibrating cylinders (Chaplin et al. 2005, Eq. 4) are functions of the same amplitude. An optional VIV AMPLITUDE section, rows TypeName AD Cv [CdAmp], gives a line type a table over the amplitude ratio A/D of the coefficient Cv that replaces its LINE TYPES Cl and a factor CdAmp (default 1) of its normal drag coefficient, linear between rows and held beyond the end ones (2 to 32 rows, A/D strictly increasing, the type with Cl > 0). Each node estimates its amplitude as Thorsen et al. do (Eq. 8 and 9): half the travel between two zero crossings of the cross-flow velocity (trapezoidal, crossings placed by linear interpolation), smoothed by a tenth of the difference per step (k_a = 0.1/dt). The velocity is taken across the ambient flow normal to the line, their incoming flow: the phase's axis across the relative flow turns with the node's own velocity and read the amplitude 16 % low at A/D 0.68. An element reads its table at the mean of its free nodes over its diameter, at the committed estimate, so the Jacobians only scale. The estimate is updated at the end of each converged step from the committed one. The estimate is four more rows of the per-node VIV motion statistics (viv_ms, CD_VIV_NMS_AMP rows with a table, CD_VIV_NMS without, so a deck without a table runs and checkpoints exactly as before), carried by the step-recovery, snapshot and system rewind paths (the system snapshot follows a line that gains tables, a restore across that change is refused) and appended to the line VIV checkpoint blocks (4 nn values). VIVAmp<L>N<J> writes the smoothed estimate [m] on a line with a table. The Python deck reader mirrors the section and channel checks; the builder writes the table (LineType.viv_amplitude). Checks: - tests/test_viv_amplitude_kernel.f90: a harmonic velocity gives the amplitude within the trapezoidal (om dt)^2/12 (1.95e-6; halving the step quarters it), the smoothing is Eq. 9 step by step, a touch of zero ends no half cycle, a growing oscillation gives each half cycle's mean amplitude within 0.1 %, tables interpolate and hold, a NaN amplitude stays inside a table, and bad tables are refused by name; - tests/test_viv_amplitude_deck.f90, on the taut gate line as an EI = 0 line and a finite-EI cable: Cv = Cl with CdAmp 1 is the deck without the section bit for bit; VIVAmp follows the steady mid-span response within 0.03 % (A/D 0.68); a Cv falling to zero at A/D 0.3 holds the response at 0.28; Cv 0 with CdAmp 2 settles at the static offset of Cd 2.4 to six digits; thirteen refusals; - tests/test_viv_coupled.f90: with tables on both lines the checkpoint blocks grow by 4 nn, the restarted run continues bit for bit, a rebuild without the VIV state does not, and a rewound step repeats; - tests/test_system.f90: a snapshot after a line gains tables is resized and restores, a restore of one taken before is refused untouched; - Python: rows read, kept and refused as natively, the builder writes them, six native/Python parity decks agree. Full ctest under both BLAS kernels, Debug -fcheck=all on the new and changed tests, pytest, ruff, mypy, Sphinx -W, pre-commit. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@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. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: ec9a00720a
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".
…he VIV rows Two review findings on the amplitude tables. A cross-flow velocity reversing exactly on a step boundary (+1, 0, -1) ended no half cycle: the zero sample overwrote the last velocity, so the following negative one saw no sign change and the travel ran on across half cycles. The travel is now carried signed, int y' dt since the last crossing (+-int |y'| dt, as y' keeps its sign between crossings), and a crossing is a change of sign from that of the running half cycle: the last velocity, or after zero samples the sign of the travel. A touch (+1, 0, +1) still ends none. For nonzero samples the amplitudes are bit-identical to before. The travel row joins the last velocity as a signed row in the checkpoint and mirror checks. An EI = 0 line that had stepped with automatic sub-stepping and then had amplitude tables set kept its two-row sub-step VIV slots, as their reuse checked the node count only; the next sub-stepped step copied six rows into two. The slots now follow both dimensions. Checks: tests/test_viv_amplitude_kernel.f90 K2, a triangular velocity sampled on its zeros ends each of its nine half cycles at y0 = 1 exactly, and the touch and reversal through one zero sample; tests/test_model.f90, tables set on the sub-stepped VIV line after 60 steps, 20 more sub-stepped steps converge with six-row slots. 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
Adds amplitude-dependent VIV coefficients. A new optional
VIV AMPLITUDEsection gives a line type a table over the cross-flow amplitude ratio A/D:Cv, which replaces the type'sCl. This is the amplitude-dependent excitation of Thorsen et al. (2016), who fit a curve C_v(y₀/D) to riser tests.CdAmp, which multiplies the type's normal drag coefficient, for drag amplification laws such as Chaplin et al. (2005, Eq. 4).The table is linear between rows and held beyond the end ones. A type takes 2 to 32 rows with A/D strictly increasing, and it needs the synchronisation lift (
Cl > 0). It works onEI = 0lines and finite-EI cables, standalone and coupled. A new channel,VIVAmp<L>N<J>, writes the smoothed amplitude estimate [m].Amplitude estimate
Each node estimates its amplitude as Thorsen et al. do (their Eq. 8 and 9):
Here$t_1, t_2$ are the last two zero crossings of $\dot y$ .
State and checkpoints
The estimate is four more rows of the per-node VIV motion statistics
viv_ms:viv_msCD_VIV_NMS= 2 (the mean squares)CD_VIV_NMS_AMP= 6 (the mean squares, then s, y₀, y₀*, last ẏ)The rows travel through the existing step-recovery, snapshot, system-rewind, checkpoint and OpenFAST-mirror paths. Two paths needed changes:
EI = 0line now check both dimensions of the statistics, so a line that gains tables after it has stepped reallocates them.Verification
test_viv_amplitude_kerneltest_viv_amplitude_deck(taut gate line,EI = 0and finite-EI)Cv = Cl,CdAmp1VIVAmpvs steady mid-span responseCvfalling to 0 at A/D 0.3Cv0,CdAmp2Cd2.4 to six digitstest_viv_coupledtest_viv_amplitude_kerneltest_modeltest_systemRun before opening:
ctestunder the default andOPENBLAS_CORETYPE=Prescottkernels;-fcheck=allon the new and changed tests;pytest,ruff,mypy, Sphinx-W,pre-commit.Docs
doc/driver_format.md: the section and theVIVAmpchannel.doc/theory.rst: the Amplitude-dependent coefficients subsection.doc/outputs.rst,doc/capabilities.rst,CHANGELOG.md.Thorsen et al. (2016) and Chaplin et al. (2005) are already in
doc/references.rst.