Repository navigation
fix(openfast): restore the held SeaState fields on a supercycled restart - #40
Conversation
A committed mooring step holds the SeaState fields sampled at its interval end at the node positions of its start. On openfast -restart the module re-sampled them at the restored, end-of-step positions. At dtM = DT this was harmless, because the next solve re-samples before any load is served; with dtM larger than DT the loads served until the next solve came from the re-sampled fields, and the restarted run drifted from the uninterrupted one (up to 2e-3 of a tension's standard deviation in the CableDyn record, on held and extrapolated loads alike). A full-precision trace placed the first difference at the first load served after the restart, with identical host inputs. The OtherState carries the held fields (fluid_held: velocity, acceleration, free-surface elevation and dynamic pressure at the line nodes), saved at Init and at every committed step, and the restart hands them back to the aggregate instead of re-sampling. A checkpoint without them re-samples as before. openfast -restart at 50 s now reproduces every later OpenFAST and .CD.out row of the IEA-15 VolturnUS-S chain mooring at dtM = 0.1 s (extrapolated and held loads) and at dtM = DT, and of the chain and power-cable mooring at dtM = 0.05 s. Uninterrupted runs do not change. 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: 9a488f41a6
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".
Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@codex review |
|
Codex Review: Didn't find any major issues. Already looking forward to the next diff. 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 coupled time-step work (#38 to #40) lets CableDyn solve on a dtM larger than the OpenFAST DT. This records the verification of that change on the IEA-15 MW VolturnUS-S chain mooring in a DLC-1.6 environment (NTM 10.6 m/s turbulent wind, JONSWAP Hs 8 m / Tp 12 s, 3800 s), at dtM = 4 DT = 0.1 s against the same model at dtM = DT and against stock MoorDyn. With the coupled loads extrapolated between CableDyn solves, every platform DOF's time series differs from the dtM = DT run by at most 0.14 % of its standard deviation (0.41 % held), the tension statistics stay within 0.16 %, and the rainflow damage-equivalent loads change by at most 0.21 % at the fairleads and 1.5 % at the anchors, of the order of the reference's own sampling effect (0.94 %). Against stock MoorDyn the in-plane platform standard deviations agree within 0.03 %. validation/scripts/openfast_supercycle_ab.py computes these figures from the twin runs; its rainflow count (ASTM E1049, four-point method, half-cycle residue, a plateau of equal samples counted once) is tested against the standard's worked example. Every statistic of a run, its DEL change included, is taken over the samples it shares with the reference, and a run covering fewer of them is flagged. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
Summary
An
openfast -restartwithdtMlarger thanDTdid not reproduce the uninterrupted run. This gap was found while verifying #39 and predates it.Cause.
dtM = DTthis was harmless, because the next solve re-samples before any load is served.Size of the drift. Up to 2e-3 of a tension's standard deviation in the CableDyn record, with held and extrapolated loads alike.
Diagnosis. A full-precision trace of every committed step and every served load placed the first difference at the first load served after the restart, with bit-identical host inputs.
Fix:
fluid_held(registry, regeneratedCableDyn_Types.f90) carries the held fields: velocity, acceleration, free-surface elevation and dynamic pressure at the line nodes. They are saved at Init and at every committed step (8 × nfluid values).Docs and records:
doc/openfast.rst(checkpoint/restart);VALIDATION.md;Verification
All runs are OpenFAST built from this branch: IEA-15 VolturnUS-S, turbulent wind and JONSWAP sea,
DT = 0.025 s. Each restart isopenfast -restartfrom the checkpoint at 50 s, and its rows after 50 s are compared text for text with the continuous run..outrows differing.CD.outrows differingdtM = 0.1 s, extrapolated loadsdtM = 0.1 s, held loadsdtM = DTdtM = 0.05 sBefore the fix, the two
dtM = 0.1 scases differed in 166 and 378.CD.outrows.dtM = DTis byte-identical to the reference.pre-commit run --all-filesand the Sphinx build with-Wpass.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