Repository navigation
feat: VIV FRAME method cycle, a lag-free frame velocity - #188
Conversation
The VIV FRAME section takes an optional third column, rows TypeName Tf
[Method]: filter (the default, the first-order filter as before) or cycle.
With cycle the frame velocity of a synchronisation type is the mean of the
node velocity over the window Tf plus half its change over it,
vbar(t) = (1/Tf) int_{t-Tf}^{t} v dt' + (v(t) - v(t-Tf))/2,
which drops a component of period Tf and its harmonics (the cross-flow VIV
and the in-line VIV at twice its frequency) and passes the slow motion of a
towed or floater-driven cable without the filter's lag; Tf is then one
period of the response. The filter's lag leaves the frame faster than the
cable on a decelerating motion and slower on an accelerating one.
The kernel (CD_VIV_Cycle_Init, CD_VIV_Cycle_Update, CD_VIV_Cycle_Valid)
samples the velocity's integral every Tf/64, exactly for the velocity linear
over a step, in a ring of 66 samples held relative to the integral at the
committed time; I(t - Tf) and v(t - Tf) come from the quadratic through the
three samples around t - Tf. Its state, 2 + 3 x 66 rows per node, sits in
the motion statistics after the frame rows on EI = 0 lines and finite-EI
cables, so step recovery, snapshots and checkpoints carry it, and a
restored state with a sample time off [0, 1] or a slot off the ring fails
closed. A line takes one method; rows without the column are unchanged to
the bit.
Tests: viv_cycle_frame (a period-Tf component and its second harmonic drop
out within 0.25 %, a ramp passes to round-off, a quadratic gives the
T^2/12 error, long steps); hermite_viv_frame F5 (moving and fixed pipe
agree, the frame follows the imposed velocity within 0.17 % against 1.7 %
for the filter, snapshot replay bit for bit); hfmf_mirror (6) checkpoint
round-trip and an invalid slot failing closed; viv_coupled (checkpoint
restart and rewind with the ring on both line kinds); viv_frame_deck G5-G7
(Method filter is the row without it to the bit, Method cycle towed and
held, refusals); viv_wake_deck W7 (the four-column row, an unknown Method
and Method cycle on a wake-oscillator type refused by name). The Python
deck checker and builder follow (viv_frame_method).
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: ce56b5c6e7
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".
A sample landing on the step end (window 1 s, steps of 0.01 s) could round the time since the latest sample a few ulps below 0, a valid simulation state that CD_VIV_Cycle_Valid then refused on a checkpoint restore. The update now clamps it to [0, h]; viv_cycle_frame C5 runs 10000 such steps and checks the state stays valid. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@codex review |
|
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". |
mypy (Python 3.10 target) wants dict[str, list[str]] for the map of a line's section types that the line-wide method check takes. 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". |
fprettify (the CI format gate, line length 120) re-indented them; the calls are split instead. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@codex review |
|
Codex Review: Didn't find any major issues. What shall we delve into next? 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
VIV FRAMEgets an optional third column,Method, with the valuesfilter(the default: the existing first-order filter, unchanged to the bit) andcycle. Withcycle, a synchronisation type's frame velocity is the lag-free cycle mean of the node velocity over the windowTf:Why
The first-order filter lags a slow motion at$\omega_m$ by $\arctan\omega_m T_f$ . A decelerating tow or floater motion therefore leaves the frame faster than the cable, and an accelerating one leaves it slower. The frame speed then differs between the two half-cycles at the same flow speed, which is a hysteresis source of the filter's own.
The cycle mean removes that lag:
Limitation
Tfmust be one period of the response. Off that period, the VIV velocity passes into the frame by aboutOn the taut cable of the deck gate, which responds at 0.29 Hz, the cable locks in at:
TfSo the method suits a response at one known frequency. A response that moves between modes keeps the filter. The docs say this.
Implementation
CableDyn_VIV:CD_VIV_Cycle_Init,CD_VIV_Cycle_Update,CD_VIV_Cycle_Valid):EI = 0lines (CD_Set_Model_VIV tf_cycle) and on finite-EI cables (CD_HermiteCable_Dyn_Set_VIV tf_cycle).CD_Set_Model_VIV_State,CD_HFMF_UnpackMirror).TypeName Tf [Method].cycleneedsCl > 0andTf > 0, so the wake oscillator keeps the filter.driver_format.md(VIV FRAME),theory.rst(flow frame, Cycle mean),capabilities.rst, andCHANGELOG.md.Tests
viv_cycle_frame(kernel):hermite_viv_frameF5:hfmf_mirror(6): the checkpoint block carries the ring, round-trips bit-identically, and a fractional slot fails closed.viv_coupled: checkpoint restart and rewind withTf 3.4 cycleon theEI = 0riser and the finite-EI cable, bit for bit.viv_frame_deckG5–G7:Method filteris the row without the column, bit for bit, on both cores.Method cycle, the towed cable responds as the held one (A/D 0.7931 against 0.7922).EI = 0).Full ctest, slow tier included: 434/434 pass (gfortran 16.2 Release, Windows, 3 jobs); python 2505 passed. The docs build is left to CI.
Effect on L3-O (published sets; not a change to the record)
These runs use the SJTU moving cylinder, with the window$T_f = 1/f_1$ = 0.373 s against the record's filter (
Tf0.2 s). The column shows the mean gap between the deceleration and acceleration paths.The method removes the filter's lag from the frame. It does not remove these sets' deceleration hold, so the record keeps the filter. Defaults are unchanged.