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
43 changes: 32 additions & 11 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -58,17 +58,17 @@ All notable changes to CableDyn are recorded in this file. The format follows
published forced-wake lift magnification within 2 %; on the taut example cable the wake locks
the cable in at its first mode (A/D 0.58 against 0.10 uncoupled) and the drag and damping take
out the wake lift's power within 0.3 %; the same line with `EI = 0` locks in within 0.1 % of
the cable's A/D at the same frequency. Its state is in the step-recovery, snapshot and
the cable's A/D, at a frequency 0.001 Hz from it. Its state is in the step-recovery, snapshot and
checkpoint state (on an `EI = 0` line, in the slots of the VIV phase and first motion
statistic); the Python deck reader and builder take the section.
- Amplitude-dependent VIV coefficients: an optional `VIV AMPLITUDE` section, rows
`TypeName AD Cv [CdAmp]`, gives a line type a table over the cross-flow amplitude ratio of the
coefficient `Cv` that replaces its `Cl` and a factor `CdAmp` of its normal drag coefficient, read
at the amplitude estimate of Thorsen et al. (2016, Eq. 8 and 9) of each node, on `EI = 0` lines
and finite-EI cables, standalone and coupled. `VIVAmp<L>N<J>` writes the estimate. On the taut
example line it follows the steady response amplitude within 0.03 %, a falling `Cv` limits the
response inside its falling range, and a table with `Cv = Cl` and `CdAmp = 1` is the line
without it, bit for bit. The estimate is in the step-recovery, snapshot and checkpoint state;
example line it follows the steady response amplitude within 0.04 % (0.1 % on an `EI = 0`
line), a falling `Cv` limits the response inside its falling range, and a table with
`Cv = Cl` and `CdAmp = 1` is the line without it, bit for bit. The estimate is in the step-recovery, snapshot and checkpoint state;
the Python deck reader and builder take the section.
- Cross-flow damping: an optional `VIV DAMPING` section row `TypeName a b [c]` splits the drag
of a finite-EI line type about the ambient normal flow: Morison's drag in line, and across it
Expand Down Expand Up @@ -116,7 +116,7 @@ All notable changes to CableDyn are recorded in this file. The format follows
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 %.
all, mean in-line displacement within 17 % in 7 of 9, cross-flow amplitude −45 % 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 All @@ -138,10 +138,10 @@ All notable changes to CableDyn are recorded in this file. The format follows
estimate (and so `Cv` and `CdAmp`) and of the axes and blend of the `VIV DAMPING` split. A cable
moved through still water had a phase input of zero cross-flow velocity, `y0 = 0`, `Cv(0)`,
`CdAmp(0)` and Morison's drag. A pipe moved at 0.6 m/s amplitude and 40 s period in still water
now gives peak A/D 0.819 against 0.819 for the same pipe held in the moving water with the
amplitude table and damping (0.711 against 0.850 without the row), and 0.713 against 0.714 with
the lift alone (0.711 against 0.736); a cable towed at 0.15 m/s gives the A/D of the cable held
in the current with the same row within 0.01 %. On `EI = 0` lines and finite-EI cables, the
now gives peak A/D 0.811 against 0.818 for the same pipe held in the moving water with the
amplitude table and damping (0.700 against 0.851 without the row), and 0.713 against 0.712 with
the lift alone (0.700 against 0.733); a cable towed at 0.15 m/s gives the A/D of the cable held
in the current with the same row within 0.02 %. On `EI = 0` lines and finite-EI cables, the
filtered velocity in rows 7-9 of the VIV motion statistics, so in the step-recovery, snapshot
and checkpoint state; `Tf` 0 or no row leaves runs unchanged to the bit. A VIV FRAME row now
needs LINE TYPES `Cl > 0` or a WAKE OSCILLATOR row; the Python deck reader and builder follow.
Expand Down Expand Up @@ -190,8 +190,29 @@ All notable changes to CableDyn are recorded in this file. The format follows
quarter now holds that tangent at its committed value, and a step that ends with a tangent
turned by 90 degrees or more fails, so the step recovery re-solves it. The line now runs at
`rho_inf` 0.5 to 1 and 25 and 50 steps per cycle, with the response of the same line seeded
at its stretch (largest A/D within 0.75 %). Every other step starts as before: every example
and test deck gives bit-identical outputs.
at its stretch (largest A/D within 0.1 %, except at `rho_inf` 1 and 25 steps per cycle, where
the VIV response is resolution-sensitive; see the time-step entry below). Every other step
starts as before: every example and test deck gives bit-identical outputs.
- A locked-in VIV response converged at first order in the time step, and at `rhoInf` 1 to a
wrong frequency: the phase of the synchronisation model (and the forcing of the wake
oscillator) sampled the generalised-alpha acceleration, which is the line's acceleration at
`t_n + (alpha_m - alpha_f) dt` only and at `rhoInf` 1 carries an undamped alternating mode of
the integrator. On a taut 20 m line locked in at 0.65 Hz the frequency changed 0.74 %, 0.41 %
and 0.27 % per halving of the step from 25 to 200 steps per cycle, and at `rhoInf` 1 it
converged 3.4 % low. The phase now advances by the implicit mid-point rule on the step's
mid-point motion, its velocity and acceleration the step means of the converged positions and
velocities, and the lift is predicted with the rate of the previous step's mid-point, a new row
of the VIV state (two with in-line VIV) carried by the step recovery, snapshots and checkpoints;
the running mean squares, the in-line phase, the flow frame's and the wake filter's filtered
velocities and the wake oscillator follow the same mid-point treatment. The response is now
second order at every `rhoInf` and does not depend on it (limits within 1e-9): the frequency
is low by about 2.2/n^2 to 3.4/n^2 at n steps per response period (doc/theory.rst; test
`viv_step_order`). The two VIV example decks change at their default `dtM` and move toward
their fine-step results (the cross-flow example's mid-span RMS from 0.31 % to 0.02 % off, its
frequency from 0.15 % to 0.018 %); every other example and test deck gives bit-identical
outputs. At `rhoInf` 1 from an unbalanced seed (tangent lengths not at the static stretch) the
response is resolution-sensitive below about 50 steps per cycle; keep `rhoInf` at or below 0.95
or seed at the stretch.

## [0.4.2] - 2026-11-09

Expand Down
8 changes: 8 additions & 0 deletions CMakeLists.txt
Original file line number Diff line number Diff line change
Expand Up @@ -1324,6 +1324,14 @@ target_link_libraries(test_viv_kernels PRIVATE cabledyn_core)
add_test(NAME viv_kernels COMMAND test_viv_kernels)
set_tests_properties(viv_kernels PROPERTIES LABELS "fortran;unit;dynamic;viv")

# Time-step convergence of a locked-in VIV response (the line and the synchronisation model or the
# wake oscillator coupled): second order in the step at rho_inf 1 and 0.4 on an EI = 0 line, and
# on a finite-EI cable; the lock-in does not move with the numerical damping.
add_executable(test_viv_step_order tests/test_viv_step_order.f90)
target_link_libraries(test_viv_step_order PRIVATE cabledyn_core)
add_test(NAME viv_step_order COMMAND test_viv_step_order)
set_tests_properties(viv_step_order PROPERTIES LABELS "fortran;integration;dynamic;viv" TIMEOUT 1200)

# Wake-oscillator kernel (Facchinetti et al. 2004): the free limit cycle, the forced lift
# magnification of their Eq. 17, and the sub-stepped Runge-Kutta advance.
add_executable(test_viv_wake_kernel tests/test_viv_wake_kernel.f90)
Expand Down
Loading
Loading