Repository navigation
feat(openfast): extrapolate the coupled loads between dtM solves - #39
Merged
Merged
Conversation
With dtM larger than the glue DT, CableDyn solves once per nsuper glue steps and held its loads between solves, so the platform received them on average dtM/2 late: a first-order lag that acts as negative damping of about the mooring stiffness times dtM/2. This is why 0.2.0 defaults to dtM = DT, at four times the mooring cost of dtM = 0.1 s. Between solves the loads are now extrapolated from the last two committed solves, F = F_c + tau (F_c - F_p) with tau the fraction of the mooring step elapsed, clamped to [0, 1]; the error is second order in dtM. The extrapolation is used only between consecutive commits, so the first step keeps the held loads. CD_UpdateStates shifts the served loads into the previous ones when a mooring step starts (not on a correction re-entry over the same step), keeping CalcOutput state-const, and mirrors them into the OtherState (pred_t, pred_loads), so a restart continues the extrapolation. The output channels and the .CD.out keep the committed samples. The deck OPTION predictLoads (default True) switches it; False keeps the hold. The arithmetic lives in CableDyn_LoadPredictor and is unit-tested. IEA-15 MW VolturnUS-S, turbulent 600 s DLC-1.6, dtM = 0.1 s against dtM = DT = 0.025 s: the platform surge, sway, roll and pitch differ by at most 0.12 % of their standard deviation (0.42 % held), on the chain and on the chain and power-cable mooring; the chain-only run takes a fifth less time (116 s against 141 s). Runs at dtM = DT are byte-identical, and with predictLoads False the outputs equal the held runs byte for byte. 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. Can't wait for the next one! 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 was referenced Oct 21, 2026
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
Second step of the coupled time-step work, after the dtM advisor (#38).
The problem. With
dtMlarger than the glueDT, CableDyn solves once pernsuperglue steps and held its loads between solves. The platform therefore received them on averagedtM/2late, a first-order lag that acts as negative damping. This is why 0.2.0 defaults todtM = DT, at four times the mooring cost ofdtM = 0.1 s.The extrapolation. Between solves, the coupled loads are now extrapolated from the last two committed solves:
F = F_c + τ (F_c − F_p), τ = (t − t_c)/dtM clamped to [0, 1]
dtM: τ(1+τ) dtM² F̈/2, against the hold's first-order lag.dtMapart), so the first mooring step keeps the held loads.How it fits the module:
CD_UpdateStates. When a mooring step starts, it shifts the loads served since the last commit into the previous ones. It does not do this on a correction re-entry over the same step.CD_CalcOutputstays state-const.pred_tandpred_loads, withCableDyn_Types.f90regenerated. A restart therefore continues the extrapolation from the same two commits..CD.outkeep the committed samples.OPTIONS predictLoadsdefaults toTrue;Falsekeeps the hold. It has no effect atdtM = DT.CableDyn_LoadPredictor, so it can be tested without OpenFAST.openfast.rst(time-step note),modeling.rst,faq.rstandoptions.rstare updated, plus the CHANGELOG.Measurement
IEA-15 VolturnUS-S, turbulent 600 s DLC-1.6,
DT = 0.025 s, againstdtM = DT, t ≥ 100 s. Each figure is the RMS of the time-series difference divided by the reference std.dtM = 0.1 s, helddtM = 0.1 s, extrapolateddtM = DT, same machine and session)dtM ≤ 0.05 s; feat(init): note a dtM that does not resolve a line's axial period #38's advisor flags it at 0.1 s.Verification
All runs below are OpenFAST built from this branch. The outputs are compared after the 8-line header, which carries the run date.
dtM = DT: the chain and mixed 600 s runs are byte-identical to the references (.outand.CD.out).predictLoads FalseatdtM = 0.1 s: byte-identical to the held-load run of the previous code.Restart (
openfast -restartat 50 s, chain,dtM = 0.1 s):.CD.out.Known, pre-existing limit, not introduced here: an
openfast -restartatdtM > DTis not bit-identical to the continuous run.dtM = DT: restarts stay bit-identical, as validated.New
load_predictorunit test:Full suite (Windows, gfortran, Release, slow tier included): 296/296. Python: 2038 passed.
pre-commit run --all-filesand the Sphinx build with-Wpass. OpenFAST builds with the regenerated registry types.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