Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -103,6 +103,11 @@ All notable changes to CableDyn are recorded in this file. The format follows
Thorsen et al. (2017) use for it: dominant strain frequency 0.992 Hz against the measured
1.00 Hz, largest r.m.s. strain 7.3 % above the measured largest, station mean 3.6 % above;
converged in mesh and time step to 0.2 %.
- Validation case L3-D (`validation/experiments/delta_flume`): cross-flow and in-line VIV of the
Delta Flume riser in the nine blind-trial stepped-current cases of Chaplin et al. (2005b), with
one generic coefficient set and the drag amplification on the in-line drag alone, against the
experimenters' measured envelopes and summaries: dominant mode right in 5 of 9 and within one in
all, mean in-line displacement within 17 % in 7 of 9, cross-flow amplitude −44 % to +4 %.
- Theory manual, Published coefficient sets: the VIV coefficient sets of Thorsen et al. (2016,
2017), Ulveseter et al. (2018), Andersen et al. (2024a, b) and Facchinetti et al. (2004), each
with its source, its test data and the line-type columns it maps to, and Thorsen et al.'s
Expand Down
19 changes: 19 additions & 0 deletions VALIDATION.md
Original file line number Diff line number Diff line change
Expand Up @@ -82,6 +82,7 @@ article's methods, are compared in
| **L3-H** | Holcombe static lazy-wave experiment | measured marker geometry | position RMSE 1.07–1.89% of suspended length; peak marker-curvature error 0.34–5.54% | end-restraint bracket | Pass |
| **L3-B** | Bergdahl chain experiment, 30 orbit conditions | measured upper-end force | RMSE 1.58 N; MAPE 3.11%; Pearson 0.993; Lin concordance 0.989 | full published matrix | Pass |
| **L3-C** | Chaplin Delta Flume riser, still-water natural frequencies | measured modes 1–7 at five tensions | mean error +1.87%, mean absolute 2.28%, largest 4.88% (34 of 35; one outlier reported) | full published table, no fitted parameter | Pass |
| **L3-D** | Chaplin Delta Flume riser in a stepped current, blind-trial cases 1–9, cross-flow and in-line VIV | measured dominant mode, peak cross-flow amplitude, mean in-line displacement, curvature standard deviations | mode right in 5/9, within one in 9/9; mean in-line within ±17% in 7/9 (−25% to +34%); cross-flow amplitude −44% to +4%; cross-flow curvature −39% to +26% | generic coefficient set, no fitted parameter | Pass measured |
| **L3-W** | SJTU steel catenary riser in 0.2 m/s current, cross-flow VIV | measured r.m.s. strain (25 stations) and dominant frequency | frequency 0.992 vs 1.00 Hz; max r.m.s. strain +7.3%, station mean +3.6% | published coefficient set, no fitted parameter | Pass |
| **L-fig** | Along-arc curvature overlay (CableDyn / OrcaFlex / MoorDyn-F ±4×) | 3-code committed record | CableDyn peak 0.11% from OrcaFlex | <0.5% | Pass |
| **L4-1** | Coupled platform + mooring | synthetic reference | bit-for-bit | — | Pass |
Expand Down Expand Up @@ -339,6 +340,24 @@ scripts, results, and source provenance are in
separately. 128 elements and ten times the unpublished axial stiffness change no frequency by
more than 3e-6 and 1.2e-4.

- **L3-D Delta Flume riser, VIV in a stepped current**
([Chaplin et al., 2005a](https://cabledyn.readthedocs.io/en/latest/references.html#ref-chaplin2005);
[Chaplin et al., 2005b](https://cabledyn.readthedocs.io/en/latest/references.html#ref-chaplin2005b)):
the nine blind-trial cases, the lower 5.94 m of the L3-C riser in 0.16–0.95 m/s, with the top
spring in series and the measured mean top tension set statically. One generic set for all
cases: cross-flow lift 0.8 (f̂0 0.18 ± 0.08), in-line C_x 0.85, α 0.15, C_D 1.2, and the drag
amplification of Chaplin et al. (2005a, Eq. 4) on the in-line drag alone (`VIV AMPLITUDE` with
`VIV DAMPING 0 0 1`). Against the experimenters' processed results, read from the vector
graphics of their blind-trial presentation: the dominant cross-flow mode is right in 5 of 9
cases and within one in the rest; the largest mean in-line displacement is within ±17% in 7 of
9 (+34% in case 2, −25% in case 9; the blind predictions under-predicted it by 20–40%);
the largest cross-flow amplitude is −44% to +4%, and the overall standard deviation of the
cross-flow curvature −39% to +26%. Half the time step and 128 elements leave the mode and
change the mean in-line displacement and the cross-flow curvature by at most 2.6% (the in-line
curvature by up to 10%), except in two cases: case 5 beats in the 40 s window (its peak
amplitude moves by up to 20%), and case 9 settles in mode 7 instead of 8 at half the time
step.

- **L3-W SJTU steel catenary riser, cross-flow VIV in uniform current**
([Wang et al., 2014](https://cabledyn.readthedocs.io/en/latest/references.html#ref-wang2014);
[Thorsen et al., 2017](https://cabledyn.readthedocs.io/en/latest/references.html#ref-thorsen2017)):
Expand Down
8 changes: 8 additions & 0 deletions doc/references.rst
Original file line number Diff line number Diff line change
Expand Up @@ -286,6 +286,14 @@ Verification and validation references
*Journal of Fluids and Structures* **21**\ (1), 3–24.
https://doi.org/10.1016/j.jfluidstructs.2005.04.010

.. _ref-chaplin2005b:

- **Chaplin, J. R., Bearman, P. W., Cheng, Y., Fontaine, E., Graham, J. M. R., Herfjord, K.,
Huera Huarte, F. J., Isherwood, M., Lambrakos, K., Larsen, C. M., Meneghini, J. R., Moe, G.,
Pattenden, R. J., Triantafyllou, M. S. & Willden, R. H. J. (2005).** Blind predictions of
laboratory measurements of vortex-induced vibrations of a tension riser. *Journal of Fluids and
Structures* **21**\ (1), 25–40. https://doi.org/10.1016/j.jfluidstructs.2005.05.016

Comparison codes
----------------

Expand Down
2 changes: 1 addition & 1 deletion doc/theory.rst
Original file line number Diff line number Diff line change
Expand Up @@ -1451,7 +1451,7 @@ The row serves two uses:

- With :math:`(0, 0, 1)` and the drag factor of :ref:`Chaplin et al. (2005) <ref-chaplin2005>`,
the amplification acts on the mean in-line drag alone, as measured, while the cross-flow drag
stays Morison's.
stays Morison's (validation case L3-D, the Delta Flume riser in a stepped current).
- :math:`(0.31, 0.89, 0)` is Thorsen's cross-flow model. It drops the linear part
:math:`\tfrac12\rho D C_{dn}U\dot y` of Morison's cross-flow damping, so it is consistent with
cross-flow VIV alone. An in-line force that turns with the relative flow can then drive an
Expand Down
2 changes: 1 addition & 1 deletion validation/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ redistributed.
| [`RELEASE_0_1_1.md`](RELEASE_0_1_1.md) | The same for v0.1.1 |
| [`RELEASE_0_1_0.md`](RELEASE_0_1_0.md) | The same for v0.1.0 |
| [`bodies/`](bodies/README.md) | Rigid-body, rod and shared-anchor cases with MoorDyn-C twins, stored references and pass limits |
| [`experiments/`](experiments/README.md) | Holcombe et al. (2025) static lazy-wave, Bergdahl et al. (2016) dynamic-chain, Chaplin et al. (2005) riser natural-frequency and Wang et al. (2014) catenary-riser VIV comparisons |
| [`experiments/`](experiments/README.md) | Holcombe et al. (2025) static lazy-wave, Bergdahl et al. (2016) dynamic-chain, Chaplin et al. (2005) riser natural-frequency and stepped-current VIV, and Wang et al. (2014) catenary-riser VIV comparisons |
| [`PERFORMANCE_0_1_0.md`](PERFORMANCE_0_1_0.md) | Wall time of CableDyn 0.1.0, MoorDyn-C and MoorDyn-F at equal accuracy on five mooring, cable, buoy and coupled cases |
| [`performance/`](performance/README.md) | Same-host wall-clock records of the L5 cases: the resolved lazy-wave spans, the one-hour VolturnUS-S mooring and the tension-only chain |
| [`PAPER_REPRODUCTION.md`](PAPER_REPRODUCTION.md) | Every CableDyn result in the journal article, re-run with the release defaults and in paper mode |
Expand Down
5 changes: 3 additions & 2 deletions validation/experiments/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

# Experimental comparisons

This directory lets reviewers reproduce CableDyn's comparisons with four published physical
This directory lets reviewers reproduce CableDyn's comparisons with five published physical
experiments. Each subdirectory gives the data source, the translation of the published
parameters into a CableDyn model, the assessed quantity, the reproduction commands and the
committed results.
Expand All @@ -12,6 +12,7 @@ committed results.
| [`holcombe/`](holcombe/README.md) | Holcombe et al. (2025), 1:70 static lazy-wave cable | Finite-EI power cable |
| [`bergdahl/`](bergdahl/README.md) | Bergdahl et al. (2016), 33 m dynamically scaled chain | Tension-only mooring chain |
| [`chaplin/`](chaplin/README.md) | Chaplin et al. (2005), 13.12 m vertical tension riser, still-water natural frequencies | Finite-EI riser, modal analysis |
| [`delta_flume/`](delta_flume/README.md) | Chaplin et al. (2005), 13.12 m vertical tension riser, stepped current, blind-trial cases 1–9 | Finite-EI riser, synchronisation VIV, cross-flow and in-line |
| [`wang_scr/`](wang_scr/README.md) | Wang et al. (2014), truncated steel catenary riser in uniform current, cross-flow VIV | Finite-EI riser, synchronisation VIV |

The results are summarised as cases L3-H, L3-B, L3-C and L3-W in [`VALIDATION.md`](../../VALIDATION.md).
The results are summarised as cases L3-H, L3-B, L3-C, L3-D and L3-W in [`VALIDATION.md`](../../VALIDATION.md).
130 changes: 130 additions & 0 deletions validation/experiments/delta_flume/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,130 @@
<!-- SPDX-License-Identifier: Apache-2.0 -->

# Delta Flume vertical riser in a stepped current: cross-flow and in-line VIV

This directory compares CableDyn's VIV with the nine blind-trial cases of the Delta Flume riser
tests. Chaplin et al. (2005a), <https://doi.org/10.1016/j.jfluidstructs.2005.04.010>, describe the
riser and the tests, and Chaplin et al. (2005b),
<https://doi.org/10.1016/j.jfluidstructs.2005.05.016>, the blind predictions made for them. The
lower 5.94 m of the 13.12 m riser is in a uniform current of 0.16–0.95 m/s, the rest in still
water. The VIV coefficients are a generic set; nothing is fitted to these measurements. The
still-water natural frequencies of the same riser are case L3-C
([`../chaplin`](../chaplin/README.md)).

## Model and data

- **Riser:** as L3-C: 13.12 m between pinned joints, D 28 mm, EI 29.9 N m², mass ratio 3.0 with
the internal water (1.847 kg/m), fresh water, C_a 1. From the project's mechanical-properties
page (University of Southampton, archived; `provenance.json`): EA 5.88 MN, structural damping
0.33 % of critical, top spring 11.4 kN/m.
- **Top spring:** in series with the riser, one effective axial stiffness
EA_eff = L/(1/k + L/EA) = 1.459e5 N. The unstretched length of each case is iterated until the
static top tension in the current is the case's mean top tension. A rigid top would turn the
current's bow into tension (1799 N instead of 1002 N in case 9) and stiffen the riser.
- **Current:** the towing speed U over the lower 5.94 m (the bottom of the carriage's vacuum
tank), still water above, with a 2 cm linear step between them.
- **Cases (slide 3 of the presentation below):**

| Case | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| U (m/s) | 0.16 | 0.21 | 0.31 | 0.40 | 0.54 | 0.60 | 0.70 | 0.85 | 0.95 |
| Mean top tension (N) | 405 | 407 | 457 | 506 | 598 | 670 | 743 | 923 | 1002 |
| Std of top tension (N) | 2 | 3 | 3 | 8 | 15 | 14 | 8 | 14 | 65 |

- **VIV (all cases):**
- synchronisation lift C_l 0.8 in the band f̂0 0.18 ± 0.08;
- in-line force C_x 0.85, α 0.15 (Ulveseter et al. 2018);
- C_D 1.2;
- a `VIV AMPLITUDE` table with C_v 0.8 constant and the drag amplification of Chaplin et al.
(2005a, Eq. 4), CdAmp = 1 + 2.3 s + 1.7 s², s = (A/D)/√2, at A/D 0–1.5;
- `VIV DAMPING` `0 0 1`: the amplification acts on the in-line drag only, and the cross-flow drag
stays Morison's.
- **Measurements:** the experimenters' processed results, from their presentation of the blind
trial (Chaplin et al., Trondheim, October 2004). The slides are vector graphics, so the values are
the plotted coordinates mapped through the tick labels, not a pixel digitisation:
- `measured_summary.csv`, from slides 17–19: maximum cross-flow displacement, maximum mean and
maximum dynamic in-line displacement (in D), and the overall standard deviation of the in-line
and cross-flow curvature (κD). Its `U` column is the speed read from each point; it matches
the tabulated speed within 0.006 m/s, which checks the axis mapping.
- `envelopes/`: the measured envelopes along the riser of each case (slides 7–15), with their
columns, checks and the assumed curvature scale in [`envelopes/README.md`](envelopes/README.md).
- The dominant cross-flow mode numbers 2, 3, 4, 5, 6, 6, 7, 7, 7 (slide 23).
- **Assumed:** the 11.4 kN/m top spring (the page also lists 38.1 kN/m, without saying which tests
used which); the 0.33 % structural damping as bending damping of a pure bending mode at 2 Hz (the
page gives no frequency).
- **CableDyn:** 64 elements; dt the largest of 5, 2.5, 2, 1 and 0.5 ms at or below 1/200 of the
shedding period D/(0.18 U) (2.5 ms in cases 1–3, 1 ms in 4–7, 0.5 ms in 8–9); `VIVrmsWindow`
0.25 s; 40 s, statistics over t > 15 s.
- **Metrics:** x is in-line and y cross-flow, both from the line between the joints.
- dominant cross-flow mode: the pinned-pinned sine with the largest r.m.s. projection of y;
- maximum cross-flow amplitude: the largest half peak-to-peak of y along the riser, against the
slide-18 maximum;
- maximum mean in-line displacement: the largest time mean of x;
- dominant cross-flow frequency (`response_comparison.csv` only): the spectral peak of y a
quarter of the length above the lower joint, at a resolution of 0.04 Hz;
- overall standard deviation of curvature: the r.m.s. over the nodes of the standard deviation
of the curvature (second differences of the node positions), times D.

## Reproduce

From the repository root, with `path/to/cabledyn.exe` the release executable or a local build:

```powershell
python validation/experiments/delta_flume/delta_flume_viv.py `
path/to/cabledyn.exe validation/experiments/delta_flume/work `
--summary validation/experiments/delta_flume
```

The nine cases run in parallel (`--jobs`), in about two minutes on a 24-core workstation. `--cases`
(for example `5,9`) selects cases; `--segments`, `--dt-scale` and `--spring` change the mesh, the
time step and the top spring.

## Results

CableDyn / measured; the measured cross-flow amplitude is the slide-18 maximum, with the half
peak-to-peak of the measured envelope in brackets.

| Case | U (m/s) | Mode | A_CF/D | Mean IL/D | Std κD, CF | Std κD, IL | Mean top tension (N) |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | 0.16 | 2 / 2 | 0.653 / 0.757 (0.763) | 1.19 / 1.06 | 5.7e-5 / 9.3e-5 | 3.5e-5 / 5.0e-5 | 409 / 405 |
| 2 | 0.21 | 3 / 3 | 0.601 / 0.579 (0.561) | 1.60 / 1.19 | 1.12e-4 / 0.89e-4 | 7.2e-5 / 3.4e-5 | 413 / 407 |
| 3 | 0.31 | 4 / 4 | 0.629 / 0.779 (0.809) | 3.27 / 3.45 | 2.06e-4 / 2.70e-4 | 0.91e-4 / 1.95e-4 | 476 / 457 |
| 4 | 0.40 | **4** / 5 | 0.692 / 0.674 (0.595) | 4.78 / 4.97 | 2.30e-4 / 3.18e-4 | 1.37e-4 / 2.69e-4 | 541 / 506 |
| 5 | 0.54 | 6 / 6 | 0.779 / 0.843 (0.889) | 6.39 / 6.69 | 4.10e-4 / 4.81e-4 | 2.10e-4 / 2.31e-4 | 656 / 598 |
| 6 | 0.60 | 6 / 6 | 0.606 / 0.709 (0.779) | 6.78 / 8.13 | 4.39e-4 / 4.77e-4 | 2.57e-4 / 4.57e-4 | 734 / 670 |
| 7 | 0.70 | **6** / 7 | 0.737 / 0.777 (0.717) | 8.32 / 8.90 | 4.68e-4 / 6.47e-4 | 2.64e-4 / 3.03e-4 | 836 / 743 |
| 8 | 0.85 | **6** / 7 | 0.781 / 0.907 (0.890) | 9.65 / 11.18 | 4.91e-4 / 6.89e-4 | 2.99e-4 / 4.48e-4 | 1046 / 923 |
| 9 | 0.95 | **8** / 7 | 0.599 / 1.074 (0.996) | 10.16 / 13.51 | 6.88e-4 / 7.36e-4 | 3.70e-4 / 6.24e-4 | 1128 / 1002 |

- **Dominant cross-flow mode:** right in 5 of 9 cases and within one in the other four (one low in
cases 4, 7 and 8, one high in case 9). Four of the eleven blind predictions found 7 or 8 of the 9
(slide 24).
- **Mean in-line displacement:** within ±17 % in 7 of 9 cases; +34 % in case 2, where the
measured maximum is 1.2 D, and −25 % in case 9. The blind predictions under-predicted the drag
amplification, and with it the mean in-line displacement, by 20–40 % (slide 26).
- **Cross-flow amplitude:** −44 % to +4 % against the slide-18 maxima (−40 % to +16 % against
the envelopes), within ±12 %, the scatter between the two measured values, in cases 2, 4, 5
and 7. The −44 % of case 9 goes with the response in mode 8.
- **Curvature:** the cross-flow standard deviation is −39 % to +26 %, low in every case but 2
(−6 % to −29 % in cases 3–9); the in-line one −53 % to +110 %. The blind predictions' r.m.s.
curvatures were 20 % to 180 % of the measured (slide 26).
- **Top tension:** the static top tension in the current is the measured mean, but the drag
amplification bows the riser further: the mean top tension of the run is 1–13 % above the
measured mean (7–13 % in cases 4–9), so the run is stiffer than the test at the higher
speeds.
- **Convergence (`provenance.json`):**
- cases 1–4 and 6–8: half the time step leaves the mode and changes the mean in-line
displacement and the cross-flow curvature standard deviation by at most 0.6 %, the peak
amplitude by at most 4.5 % and the in-line curvature by at most 10 % (case 8); 128 elements
leave the mode and change them by at most 2.6 %, 4.2 % and 9 %;
- case 5 beats in the 40 s window: its peak amplitude changes by −17 % and −20 % and its
in-line curvature by −10 % and +25 %, while the other metrics move by at most 9 %;
- case 9 has two responses: at half the time step it settles in mode 7 (5.80 Hz, A/D 0.725,
mean in-line displacement 10.63 D), with the base step and with 128 elements in mode 8
(6.60 Hz), which an 80 s run keeps.
- **Top spring 38.1 kN/m (`--spring 38.1e3`):** the mean top tension of the run is up to 14 %
higher and the mean in-line displacement 2–16 % lower, within ±17 % in 4 of 9 cases; the mode
is right in 5 of 9 (case 9 in mode 7, case 5 in mode 5, case 8 in mode 5).

`response_comparison.csv` holds the per-case values with their errors, and `summary.json` the
statistics and the SHA-256 of the executable.
Loading
Loading