Skip to content

validation: SJTU flexible cylinder VIV in oscillatory flow (L3-O) - #180

Merged
SMI-Lab-Inha merged 1 commit into
devfrom
feat/validation-fu-oscillatory
Nov 17, 2026
Merged

SMI-Lab-Inha merged 1 commit into
devfrom
feat/validation-fu-oscillatory

Conversation

@SMI-Lab-Inha

Copy link
Copy Markdown
Owner

Summary

Validation case L3-O: the SJTU flexible cylinder of Fu et al. (2014), moved harmonically across its axis through still water.

  • Cylinder: 4 m, D 24 mm, EI 10.5 N m², pretension 500 N.
  • Motion: A_m 0.68 m (KC 178) at periods 16.5, 10.2 and 8.45 s, so U_R,max is 4, 6.5 and 7.9.

The relative flow reverses twice per cycle, so this case tests what a steady current cannot:

  • the VIV models through flow reversal;
  • the response on the accelerating and decelerating halves of each half-cycle, where Fu et al. measure different amplitudes (hysteresis).

No model parameter is fitted to these tests.

What is compared

  • A/D paths: the cross-flow A/D at mid-span (station CF4), plotted against the instantaneous U_R = |V|/(f₁D) on both paths. It is compared with the measured paths of Figs. 15–17.
  • Lock-in share: the share of each half-cycle the envelope spends above √2/2 of its peak. This is the article's definition; it gives about 17, 34 and 50 %.
  • Coefficient sets: the three published sets of the FLOTANT and NDP cases (uls19, b1, wake).

Results (primary runs)

U_R,max Set A/D r.m.s. error Mean gap dec. − acc. (measured) Largest A/D (measured) Lock-in share (measured)
4 uls19 0.079 −0.005 (+0.009) 0.124 (0.286) 0.08 (0.17)
4 b1 0.138 +0.123 (+0.009) 0.472 (0.286) 0.31 (0.17)
4 wake 0.088 +0.106 (+0.009) 0.280 (0.286) 0.27 (0.17)
6.5 uls19 0.340 +0.426 (+0.089) 1.007 (0.475) 0.34 (0.34)
6.5 b1 0.339 +0.364 (+0.089) 0.874 (0.475) 0.53 (0.34)
6.5 wake 0.177 +0.271 (+0.089) 0.609 (0.475) 0.46 (0.34)
7.9 uls19 0.338 +0.498 (+0.123) 1.043 (0.450) 0.34 (0.50)
7.9 b1 0.345 +0.380 (+0.123) 0.937 (0.450) 0.60 (0.50)
7.9 wake 0.132 +0.255 (+0.123) 0.570 (0.450) 0.50 (0.50)
  • Flow reversal: every run converges through it.
  • U_R,max 4: the wake oscillator gives the measured largest A/D. The generic set is 65 % high, and uls19 barely responds.
  • U_R,max 6.5 and 7.9: every set holds the lock-in while the flow slows.
    • The gap between the paths is 2–5 times the measured one, and the largest A/D is 1.3–2.3 times the measured.
    • The measured hysteresis is the same in kind but smaller in size.
    • The FLOTANT case shows the same persistence: its lock-in releases late.
  • Without the VIV FRAME row: the generic set scores 0.034 at U_R,max 4, the best of any run, but still holds the lock-in at 6.5 and 7.9.

Convergence and reproducibility

  • Half the time step and 80 elements (at U_R,max 6.5): change the largest A/D by at most 0.1 % for b1 and wake, and by 4.1 % for uls19.
  • Tf 0.1 and 0.3 s: move the synchronisation sets' largest A/D by up to 21 %, and the wake oscillator's by up to 11 %.
  • Reproducibility: the default command, run into a new work directory, reproduces response_comparison.csv and summary.json byte for byte.

Data

  • extract_fu2014.py reads the paths from the article's PDF. Figs. 15–17 are raster images.
    • It calibrates each figure on its plot frame and masks the inset, the legend, the title box and the tick marks.
    • It follows each line by colour and bridges the arrowheads.
    • The traced gaps between the paths, 0.164 at U_R 3.5 and 0.222 at U_R 4, match the figures' own annotations, 0.15D and 0.2D.
  • Limitations, stated in the README:
    • the measured A/D is reconstructed from strain with constant-tension modes;
    • the submergence, the band-pass cut-offs and the structural damping are not given;
    • the comparison covers one station and three cases;
    • the lock-in shares are "about" values.

Docs

  • VALIDATION.md gains a table row and a section.
  • The experiments indexes, the top-level README (now eight experiments), the changelog and doc/references.rst are updated. The Fu et al. (2014) reference was checked against the article's first page and footers.

Checks

  • ctest: documentation_sources and validation_records pass.
  • ruff: check and format are clean on both scripts.
  • Sphinx: the local build is blocked by an environment problem: the docs venv's numpy cannot register its DLL directory from the long scratchpad path. The CI sphinx-build -W job covers it.

The tests of Fu, Wang, Baarholm, Wu & Larsen (2014): a 4 m flexible
cylinder (D 24 mm, EI 10.5 N m^2, pretension 500 N) moved across its axis
through still water, A_m 0.68 m (KC 178) at periods 16.5, 10.2 and 8.45 s
(U_R,max 4, 6.5 and 7.9). The relative flow reverses twice per cycle, so
the case tests the VIV models through flow reversal and on the
accelerating and decelerating halves of each half-cycle, where Fu et al.
measure different amplitudes (hysteresis).

validation/experiments/fu_oscillatory/fu_oscillatory_viv.py writes a deck
per run, runs them in parallel (reused when deck and executable are
unchanged) and compares the cross-flow A/D at mid-span (station CF4)
against the instantaneous U_R on the two paths with the measured paths of
Figs. 15-17, and the share of each half-cycle above sqrt(2)/2 of its
peak with the article's lock-in shares (about 17, 34 and 50 %).
extract_fu2014.py reads the paths from the figures, raster images
calibrated on the plot frame and traced by colour; the traced gaps between
the paths (0.164 at U_R 3.5, 0.222 at 4) match the figures' annotations
0.15D and 0.2D.

Three published sets, none fitted to these tests (uls19, b1, wake, as in
the FLOTANT and NDP cases), each with a VIV FRAME row: the cylinder moves
through still water, where without it the wake oscillator never sheds.
The primary runs take Tf 0.2 s; the motion period is 23-44 periods of f1,
around the 30 the frame's two conditions need, so the record reports the
runs without the row and with Tf 0.1 and 0.3 s.

Results (A/D r.m.s. error over both paths; largest A/D):
- every run converges through the flow reversals;
- U_R,max 4: the wake oscillator gives the measured largest A/D (0.280
  against 0.286), the generic set is 65 % high, uls19 barely responds;
- U_R,max 6.5 and 7.9: every set holds the lock-in while the flow slows,
  the mean gap between the paths 2-5 times the measured one and the
  largest A/D 1.3-2.3 times the measured; the wake oscillator comes
  closest (0.177 and 0.132).
Without the row the generic set scores 0.034 at U_R,max 4, the best of
any run, but keeps the deceleration hold at 6.5 and 7.9.

Half the time step and 80 elements change the largest A/D by at most
0.1 % (generic set, wake oscillator) and 4.1 % (uls19). The default
command run into a new work directory reproduces response_comparison.csv
and summary.json byte for byte.

Added to VALIDATION.md as L3-O, to the experiments indexes, the top-level
README, the changelog and the references (Fu et al. 2014, from the
article's first page and footers).

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 Nov 17, 2026 •

Copy link
Copy Markdown
Codex Review Summary: ✅ Completed

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

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-11-17T10:33:59.806574Z 087712f 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.

@read-the-docs-community

Copy link
Copy Markdown

Documentation build overview

📚 CableDyn | 🛠️ Build #35953399 | 📁 Comparing 087712f against latest (789cb6d)

  🔍 Preview build  

15 files changed · ± 15 modified

± Modified

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. Bravo.

Reviewed commit: 087712f338

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 b49dddb into dev Nov 17, 2026
16 checks passed
@SMI-Lab-Inha
SMI-Lab-Inha deleted the feat/validation-fu-oscillatory branch November 17, 2026 12:41
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