Skip to content

validation: NDP 38 m high-mode riser VIV in uniform flow (L3-N) - #172

Merged
SMI-Lab-Inha merged 2 commits into
devfrom
feat/validation-ndp
Nov 16, 2026
Merged

SMI-Lab-Inha merged 2 commits into
devfrom
feat/validation-ndp

Conversation

@SMI-Lab-Inha

Copy link
Copy Markdown
Owner

Summary

Adds validation case L3-N, validation/experiments/ndp_riser/. It compares CableDyn's VIV with the bare-riser uniform-flow tests of the Norwegian Deepwater Programme high-mode riser (Trim et al. 2005).

The riser is 38 m long and 27 mm in diameter. It was towed at 22 speeds from 0.3 to 2.4 m/s and responded at up to 12.5 Hz cross-flow. Results are on the second-order VIV phase update (#171).

  • Riser: pinned, EI 598.8 N m², EA 8.19e6 N, 0.933 kg/m flooded, in fresh water.
  • Tension rig: an axial spring in series, $EA_\text{eff} = L/(1/k_{ax} + L/EA)$, with 4 kN in still water. $k_{ax} = 3.5$ kN/m is derived from the reported 4–6 kN range, not from the response.
  • Measurements:
    • maximum r.m.s. CF strain (Thorsen et al. 2016, Fig. 8), read from the vector graphics;
    • σ/D CF and IL at all 22 speeds, and the dominant frequencies at five speeds (Trim et al. 2005, Figs. 16 and 18). These figures are raster, read on enlarged crops with stated uncertainties.
  • Coefficient sets: each published value was checked against its source. Each set is marked by whether its authors fitted it to these tests:
Set Fitted to these tests?
b1: the generic set of the Delta Flume case no: blind
and24b: Andersen et al. 2024b, cross-flow average to the sheared-flow tests of this riser
uls19: Ulveseter et al. 2019 to these uniform-flow tests (an implementation check)
th16: Thorsen et al. 2016, fitted $C_v(y_0/D)$ to these tests (an implementation check)
th16c: th16 with Morison's linear CF damping kept variant

Results (22 speeds, 200 elements, dt 1 ms)

Set Strain ratio, median (range) rms log error $fD/U$ (meas. 0.143) σ/D CF (0.436) σ/D IL (0.149)
b1 1.26 (0.99–1.57) 0.277 0.192 0.429 0.041
and24b 1.00 (0.67–1.27) 0.186 0.134 0.687 0.088
uls19 0.89 (0.64–1.33) 0.178 0.145 0.461 0.146
th16 1.40 (0.91–1.86) 0.363 0.193 0.390 0.067
th16c 0.73 (0.51–1.06) 0.365 0.153 0.307 0.025
Thorsen et al.'s own simulation 1.12 (0.75–1.51) 0.187
  • uls19: the only set that matches strain, frequency and both σ/D together (σ/D within 6 % CF and 3 % IL). Its strain error is the lowest, but only 0.008 below and24b, which is inside the spread below.
  • and24b: equals Thorsen et al.'s own fit on strain, but its σ/D is 57 % high. A lower mode at a larger amplitude gives the same curvature.
  • Blind b1: σ/D CF within 2 %, but the frequency is a third high and the median strain 26 % high.
  • th16 and th16c: the damping form sets the frequency (0.193 against 0.153). Their strain errors are now nearly equal.

Analysis choices

  • Curvature components: the CF curvature is CurvX. Its section axis starts vertical at End A and stays within 2° of vertical on the bowed riser. Choosing the component by its static mean would pick the in-line one below about 0.45 m/s, where weight sag exceeds drag bow.
  • Dominant frequency: searched only in $fD/U$ 0.05–0.30. This excludes the slow swing of the riser and the third harmonic of uls19.

Convergence (provenance.json)

  • 1.0 m/s:

    • half the time step and 400 elements change the strain of four sets by at most 0.8 %, and σ/D by at most 3 %;
    • uls19 moves by +1.9 % and +18.5 %, and responds at 5.60 Hz instead of 5.80 Hz.
  • 2.4 m/s: not converged speed by speed.

    • The strain moves by −14 % to +12 % with half the time step and by +0.6 % to +20 % with 400 elements.
    • The dominant frequency moves by more than one bin in 7 of 10 pairs.
    • A 55 s run moves th16c by +12.5 %. At 55 s the step and mesh still move the three sets by up to 21 %, so a longer window does not remove the spread. The README says so and puts it down to the mix of neighbouring high modes, about the size of the speed-to-speed scatter.
  • Full sweep at dt/2:

    • rms log errors 0.280 / 0.187 / 0.184 / 0.375 / 0.376 (b1 / and24b / uls19 / th16 / th16c);
    • $fD/U$ within 0.001 and σ/D within 1.4 % of the record.

    The aggregates hold, and differences of a few hundredths between sets are within this spread.

  • Sea water (1025 kg/m³), U ≥ 0.5 m/s:

    • rms log errors 0.299 / 0.181 / 0.154 / 0.434 / 0.353;
    • th16 moves most.

Checks

  • pre-commit on the changed files.
  • Full test suite: 428/428 on this branch.
  • Reproducibility: the default 25-run invocation reproduces its rows of the committed full sweep exactly.
  • Indexes: the case is listed in VALIDATION.md, validation/README.md, validation/experiments/README.md, doc/references.rst (Trim et al. 2005 and Fontaine et al. 2011, from Crossref) and the CHANGELOG. The top-level README now names the six published experiments; it listed two.

The bare riser of the Norwegian Deepwater Programme tests (Trim et al.
2005, J. Fluids Struct. 21(3), 335-361) towed horizontally at its 22
uniform-flow speeds, 0.3-2.4 m/s, responding at up to 12.5 Hz across
the flow. It tests high-mode cross-flow VIV against four coefficient
sets on one model, one of them blind.

validation/experiments/ndp_riser/ndp_riser_viv.py writes a deck per set
and speed: 38 m between universal joints, D 27 mm, EI 598.8 N m^2, EA
8.19e6 N, 0.933 kg/m flooded (Fontaine et al. 2011, Table 1), fresh
water (the mass ratio 1.62 implies 1006 kg/m^3), the clump-weight rig
as an axial spring in series, EA_eff = L/(1/k_ax + L/EA), with T0 4 kN
in still water and k_ax 3.5 kN/m derived from the reported 4-6 kN range,
not tuned. 200 elements, dt 1 ms, 25 s, statistics after 10 s, CurvX
and CurvY at every node. It runs the sets in parallel (--sets,
--speeds; the default 25 runs take about two minutes, the full
110-run sweep of the committed record about eight on 24 cores) and
compares the maximum r.m.s. cross-flow strain (fundamental, band-passed
about the dominant frequency as Thorsen et al. 2016 filter the
measurement), the dominant frequency f D/U and the spatial-mean sigma/D.
CurvX is the cross-flow curvature (the section axis starts vertical
at End A); the dominant frequency is searched for in f D/U 0.05-0.30,
which keeps a slow swing and the third harmonic out.

Sets, each as its source gives it, checked against the articles:
- b1, the generic set of the Delta Flume case (Cl 0.8, cF 0.18, dF
  0.08, ClX 0.85, alpha 0.15, Chaplin's drag amplification on the
  in-line drag via VIV DAMPING 0 0 1): blind;
- and24b, Andersen et al. (2024b), Table 3, cross-flow average (Cl 1.28,
  cF 0.131, dF 0.066, Cd 1.16), fitted to the sheared-flow tests of the
  same riser;
- uls19, Ulveseter et al. (2019), Table 1 (Cl 0.85, cF 0.144, dF 0.064,
  ClX 0.75, alpha 0.15, Chh 1.5), fitted to these tests;
- th16, Thorsen et al. (2016), the C_v curve of their Fig. 7 and their
  cross-flow damping (VIV DAMPING 0.31 0.89 0), fitted to these tests;
  th16c keeps Morison's linear cross-flow damping (a variant).

Measurements: the maximum r.m.s. cross-flow strain of each test with
Thorsen et al.'s own simulation, read from the vector graphics of their
Fig. 8 (extract_thorsen2016.py, which also reads the Fig. 7 curve), and
sigma/D and the dominant frequencies of Trim et al.'s Figs. 16 and 18,
read by eye on enlarged guided crops of the raster figures
(digitise_trim2005.py draws them; +-0.01 in sigma/D, +-0.3 Hz).

Result (22 speeds; r.m.s. log error of the strain, f D/U against the
measured 0.143, sigma/D CF against 0.436):
- uls19 0.165, 0.143, 0.460: matches strain, frequency and amplitude
  (IL sigma/D 0.147 against 0.149); Thorsen et al.'s own fitted
  simulation scores 0.187;
- and24b 0.186, 0.134, 0.690;
- b1 0.283, 0.191, 0.435;
- th16 0.354, 0.183; th16c 0.418, 0.158: keeping the linear damping
  lowers the response frequency towards the measured one.

At 1.0 m/s half the time step and 400 elements move the strain by at
most 0.9 % for four sets (7.4 % for uls19); at 2.4 m/s the mix of
neighbouring high modes moves it by up to 39 %, while a 55 s run
changes it by under 4 %. The 22-speed statistics hold: the full sweep
at half the time step gives 0.279, 0.191, 0.189, 0.373 and 0.381, f D/U
within 0.004 and sigma/D within 1.2 %.

Added to VALIDATION.md as L3-N, to the experiments index, the
changelog and the references (Trim et al. 2005, Fontaine et al. 2011,
checked against Crossref).

Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
The full sweep (5 sets, 22 speeds) and every sensitivity run in
provenance.json (half the time step, 400 elements, the 55 s runs, the
full sweep at half the time step, sea water) rerun on the second-order
VIV phase update.

Strain r.m.s. log error: uls19 0.178 (0.165 before), and24b 0.186
(0.186), b1 0.277 (0.283), th16 0.363 (0.354), th16c 0.365 (0.418);
Thorsen et al.'s own simulation 0.187. f D/U 0.145, 0.134, 0.192, 0.193
and 0.153 against the measured 0.143. uls19 still matches strain,
frequency and sigma/D together (sigma/D within 6 % cross-flow and 3 %
in line).

At 1.0 m/s, half the time step and 400 elements move the strain of four
sets by at most 0.8 %; uls19 by +1.9 % and +18.5 %, at 5.60 Hz instead
of 5.80 Hz. At 2.4 m/s the strain moves by -14 % to +12 % with half the
time step (-31 % to +22 % before) and by +0.6 % to +20 % with 400
elements (-39 % to +0.5 %). The 55 s run of th16c at 2.4 m/s moves its
strain by +12.5 % (+2.2 % before), and at 55 s the step and mesh still
move the three sets by up to 21 %, so the README no longer says the
25 s window is long enough: a longer window does not remove the
spread. The full sweep at half the time step gives 0.280, 0.187, 0.184,
0.375 and 0.376, f D/U within 0.001 and sigma/D within 1.4 %. Sea
water: 0.299, 0.181, 0.154 (uls19, now listed), 0.434 and 0.353 from
0.5 m/s; th16 moves most.

The top-level README now lists the six published experiments (it named
two).

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 16, 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 2026-11-16T10:18:50.281397Z 211ba98 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 #35923349 | 📁 Comparing 211ba98 against latest (789cb6d)

  🔍 Preview build  

14 files changed · ± 14 modified

± Modified

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. Keep them coming!

Reviewed commit: 211ba98f0e

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 05a4f14 into dev Nov 16, 2026
16 checks passed
@SMI-Lab-Inha
SMI-Lab-Inha deleted the feat/validation-ndp branch November 16, 2026 12:27
SMI-Lab-Inha added a commit that referenced this pull request Nov 16, 2026
…r and bending-damping speed-ups (#173)

viv_long_run runs the synchronisation model for 400 cycles. Prescribed
motion: every node of a finite-EI cable moves across a 0.3 m/s flow as a
rigid body, so the shedding phase obeys Adler's equation,
d psi/dt = a - b sin(psi), solved in closed form. Outside the band
(5.5 rad/s) the error grows linearly in time (T/(T/2) 2.014 and 1.988 at
50 and 100 steps per cycle) and is second order (4.01 from 50 to 100
steps): 0.0167 rad after 400 cycles at 100 steps per cycle. Inside the
band the lag holds within 3.0e-5 rad of psi*, the averaging-ripple
floor, and the mean rate is the motion's within 5.8e-12.

Lock-in, finite-EI and EI = 0 (taut 20 m line, rho_inf = 1, no added
mass, 100 and 200 steps per cycle): the load powers close E(t) - E(0) to
2.0e-4 / 1.8e-4 of the VIV work, second order (3.98 / 3.67) and
stationary (T against T/2 1.00). On the mid-point phase update of #171
the lift takes the phase predicted from the previous step's mid-point
rate, half a step behind, so the bound is 3e-4. The halves agree in RMS
A/D within 7.3e-4, VIV power within 1.8e-3 and lock-in frequency within
1.9e-4; the frequency changes by 1.6e-4 / 1.9e-4 from 100 to 200 steps
per cycle. Every tolerance and its measured value is in the test header.
57 s Release; label slow, TIMEOUT 1200.

run_study with jobs > 1 runs every case with OMP_NUM_THREADS=1 unless the
environment sets it, and study.json records omp_num_threads. On a 24-core
workstation (gfortran Release) 96 finite-EI VIV cases scale 13.3x at 24
jobs and 15.1x at 48; on the 1024-element lazy-wave example 24 jobs take
16.7 s with one thread each, 17.9 s with four and 19.1 s with the OpenMP
default. The Python manual gives the table and the recommended settings.

Speed-ups, outputs bit-identical:
- a row evaluates a line's node powers once for all its power channels
  (VIVPow, DragPow, DampPow; 19 % of a VIV run) on the Hermite, EI = 0
  and system routes; any failure still goes through the
  channel-at-a-time path. viv_taut_cable_inline.dat 2.39 s to 2.14 s;
- the bending damping force no longer computes the second derivatives
  of the curvature, which only the position Jacobian uses (32 % of the
  Delta Flume case 9 run): 73.2 s to 58.6 s.
load_power_deck P6 checks that a power channel read alone equals the
same channel among its line's other power channels, on all three routes.

Checked: 431/431 tests on the default and the Prescott OpenBLAS kernel;
the 134 example and test-data decks bit-identical to the reference
build; the NDP validation runs of #172 reproduce their committed rows.

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