Skip to content

fix(openfast): restore the held SeaState fields on a supercycled restart - #40

Merged
SMI-Lab-Inha merged 2 commits into
devfrom
fix/supercycle-restart
Oct 21, 2026
Merged

SMI-Lab-Inha merged 2 commits into
devfrom
fix/supercycle-restart

Conversation

@SMI-Lab-Inha

@SMI-Lab-Inha SMI-Lab-Inha commented Oct 21, 2026 •

Copy link
Copy Markdown
Owner

Summary

An openfast -restart with dtM larger than DT did not reproduce the uninterrupted run. This gap was found while verifying #39 and predates it.

Cause.

  1. A committed mooring step holds the SeaState fields sampled at its interval end, at the node positions of its start.
  2. On restart, the module re-sampled them at the restored, end-of-step positions.
  3. At dtM = DT this was harmless, because the next solve re-samples before any load is served.
  4. With supercycling, the loads served until the next solve came from the re-sampled fields, and the restarted run drifted.

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:

  • A new OtherState array fluid_held (registry, regenerated CableDyn_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).
  • The restart hands them back to the aggregate instead of re-sampling.
  • Re-sampling remains only as a defensive fallback. Init saves the first fields, so a checkpoint of an instance that takes host fluid always carries them.
  • Checkpoint layout. The layout changes, here and with feat(openfast): extrapolate the coupled loads between dtM solves #39's predictor fields. OpenFAST checkpoints are not versioned, so a checkpoint written by an earlier CableDyn cannot be restarted with this one; the CHANGELOG says so.

Docs and records:

  • doc/openfast.rst (checkpoint/restart);
  • the restart row of VALIDATION.md;
  • CHANGELOG.

Verification

All runs are OpenFAST built from this branch: IEA-15 VolturnUS-S, turbulent wind and JONSWAP sea, DT = 0.025 s. Each restart is openfast -restart from the checkpoint at 50 s, and its rows after 50 s are compared text for text with the continuous run.

case .out rows differing .CD.out rows differing
chain, dtM = 0.1 s, extrapolated loads 0 / 500 0 / 500
chain, dtM = 0.1 s, held loads 0 / 500 0 / 500
chain, dtM = DT 0 / 500 0 / 2000
chain + 248-element power cable, dtM = 0.05 s 0 / 500 0 / 1000

Before the fix, the two dtM = 0.1 s cases differed in 166 and 378 .CD.out rows.

  • Uninterrupted runs: the 600 s chain run at dtM = DT is byte-identical to the reference.
  • Full suite (Windows, gfortran, Release, slow tier included): all pass. Python: 2038 passed. pre-commit run --all-files and the Sphinx build with -W pass.

Checklist

  • pre-commit run --all-files passes
  • ctest --test-dir build --output-on-failure passes
  • python -m pytest tests python/tests passes (if Python or validation records changed)
  • VALIDATION.md updated if a validation result changed
  • CHANGELOG.md updated under [Unreleased] (heading added if missing) for user-visible changes
  • Documentation in doc/ updated for changed inputs, options, or outputs
  • Conventional Commit title (feat:, fix:, docs:, ...)
  • Commits are signed off (git commit -s) under the
    Developer Certificate of Origin

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>
@SMI-Lab-Inha

Copy link
Copy Markdown
Owner Author

@codex review

@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Oct 21, 2026 •

Copy link
Copy Markdown

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-10-21T11:15:00.707912Z ed4c3a4 Manual request
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" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 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".

Comment thread src/openfast/CableDyn_Types.f90 Resolved
@read-the-docs-community

read-the-docs-community Bot commented Oct 21, 2026 •

Copy link
Copy Markdown

Documentation build overview

📚 CableDyn | 🛠️ Build #35295298 | 📁 Comparing ed4c3a4 against latest (d3ddfeb)

  🔍 Preview build  

8 files changed · ± 8 modified

± Modified

Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
@SMI-Lab-Inha

Copy link
Copy Markdown
Owner Author

@codex review

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. Already looking forward to the next diff.

Reviewed commit: ed4c3a4516

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".

@SMI-Lab-Inha
SMI-Lab-Inha merged commit ec3c6d9 into dev Oct 21, 2026
15 checks passed
@SMI-Lab-Inha
SMI-Lab-Inha deleted the fix/supercycle-restart branch October 21, 2026 14:54
SMI-Lab-Inha added a commit that referenced this pull request Oct 22, 2026
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>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant