Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
31 commits
Select commit Hold shift + click to select a range
b5c647f
fix: exclude OpenBLAS 0.3.34 from the development environment (#7)
SMI-Lab-Inha Oct 14, 2026
69cbe6a
perf: evaluate each directional-sea phase and depth profile once (#9)
SMI-Lab-Inha Oct 14, 2026
0213290
feat: add a run-time profile to the standalone driver (#8)
SMI-Lab-Inha Oct 14, 2026
4d706a9
perf: reuse the clamped-cable Jacobian columns across body steps (#10)
SMI-Lab-Inha Oct 14, 2026
13452d0
feat: run lines restrained in torsion in coupled OpenFAST runs (#11)
SMI-Lab-Inha Oct 14, 2026
1e25ca2
test: compare the linearisation and FAST.Farm runs with MoorDyn (#12)
SMI-Lab-Inha Oct 14, 2026
330a815
test: hold the vertical coupled-torsion lines taut (#13)
SMI-Lab-Inha Oct 14, 2026
8878f99
fix: carry the end weight moment at an anchor resting on the seabed (…
SMI-Lab-Inha Oct 15, 2026
0e2e511
fix: refine coarse finite-EI statics that fail the stability test (#15)
SMI-Lab-Inha Oct 15, 2026
1446317
fix: static equilibria over non-planar bathymetry (#16)
SMI-Lab-Inha Oct 15, 2026
b32d3f4
feat: OrcaFlex "as laid" seabed friction in statics (#17)
SMI-Lab-Inha Oct 16, 2026
f2caf1f
feat(capi): host-coupling calls for CFD hosts (ABI 1.2) (#18)
SMI-Lab-Inha Oct 16, 2026
4dfbc7a
perf: faster tension-only line steps; refactor the junction tangent a…
SMI-Lab-Inha Oct 16, 2026
c66918c
fix(dynamics): stop EI=0 tension spikes at slack/taut switching (#20)
SMI-Lab-Inha Oct 16, 2026
71158d5
feat(outputs): equilibrium tension recovery, continuous touchdown, an…
SMI-Lab-Inha Oct 16, 2026
73bd063
feat(rods): pinned and coupled-pinned rods on the coupled route (#22)
SMI-Lab-Inha Oct 17, 2026
10a7b14
fix(outputs): node channels report the deck node on refined lines (#23)
SMI-Lab-Inha Oct 17, 2026
b687d09
feat(openfast): warn when line nodes lie outside the SeaState wave gr…
SMI-Lab-Inha Oct 19, 2026
d2387ee
feat(dynamics): sub-step EI = 0 steps that turn or snap taut (#25)
SMI-Lab-Inha Oct 19, 2026
065df73
feat(control): active tension of finite-EI cables; committed lengths …
SMI-Lab-Inha Oct 20, 2026
256157f
fix: whole diagnostic messages; name causes and workarounds (#27)
SMI-Lab-Inha Oct 20, 2026
b8594fd
fix: seabed contact for clump points and buoys; note EI = 0 folds (#28)
SMI-Lab-Inha Oct 20, 2026
cd1aaa5
fix(statics): refine locally; robust attachment polish (#29)
SMI-Lab-Inha Oct 20, 2026
391a8ba
chore(release): prepare CableDyn 0.2.0 (#30)
SMI-Lab-Inha Oct 20, 2026
3c066f4
fix: accept seabed recompute inputs equal to rounding (#31)
SMI-Lab-Inha Oct 20, 2026
e5389b6
chore(release): record the builds and checks of 0.2.0
SMI-Lab-Inha Oct 20, 2026
1a56ccd
fix(bathymetry): bound the crease rounding of neighbouring cells
SMI-Lab-Inha Oct 20, 2026
abe441f
fix(python): per-line friction options follow their line
SMI-Lab-Inha Oct 20, 2026
fff7d86
chore(release): record the final 0.2.0 builds and checks
SMI-Lab-Inha Oct 20, 2026
9e48281
fix(outputs): keep the touchdown point continuous on steep stencils
SMI-Lab-Inha Oct 20, 2026
d3ddfeb
chore(release): record the 0.2.0 assets of the final tree
SMI-Lab-Inha Oct 20, 2026
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
25 changes: 22 additions & 3 deletions ARCHITECTURE.md
Original file line number Diff line number Diff line change
Expand Up @@ -193,7 +193,16 @@ The effective tangent is `(1 − α_m)/(β Δt²) M + (1 − α_f) K_q +
1e-14, 30 iterations, 12 backtracks. A non-converged step, or on the Hermite path
an under-resolved one, is repeated by internal subdivision (4, 16, … up to
`recovery_max_substeps`) along a C² quintic boundary trajectory that ends on the
host time.
host time. On `EI = 0` lines `CD_Step_Model` also re-solves a converged step in
`max(4, ceil(turn/ei0_substep_angle))` sub-steps on the same trajectory when a
taut segment turned by more than `ei0_substep_angle` or a slack segment snapped
taut while the step does not resolve its axial wave (`ei0_substeps auto`, the
default; at most `ei0_substep_max`). It restores the committed kinematics and
constitutive and friction states first (`commit_state_copy`, the one list of
that state in `CableDyn_Model`) and keeps the plain step when a sub-step fails.
The sub-steps of a recovered step, the halves of a line-system step halved by
`CD_Step_System`, and the lines attached to the objects of the monolithic
body/point step are taken as given.

### Bodies, rods, and points

Expand Down Expand Up @@ -376,6 +385,12 @@ the exchange buildable and testable without OpenFAST.
carry `app/utf8_code_page.manifest`, which makes UTF-8 the process code page, so
the Fortran runtime opens any name as written; a GNU build falls back to 8.3
short names for characters outside the system ANSI code page.
- **Run-time profile** (`CableDyn_Profile`): with `CABLEDYN_PROFILE` set, the standalone
driver charges its wall time to the phase that is running. Every time march marks where its
fluid update, step, checks, output and progress report begin, so a run that stops with an
error keeps its time in the phase it stopped in. The driver counts the `EI = 0` line steps and
Newton iterations in `CD_Step_Model`, and reports them with the finite-EI step counters of
`CableDyn_HermiteCableDynamic`. Unarmed, each mark is one test of a flag.
- **C-ABI handles** (`cabledyn_mutex.c`): the handle registry is guarded by a
spin-yield lock and deck initialisation by an input lock; operating on a handle
while closing it from another thread is outside the API contract.
Expand All @@ -395,6 +410,7 @@ src/
cabledyn_mutex.c C-ABI registry and initialisation locks
cabledyn_crt_locale.c MinGW-w64 guard for libgfortran's locale restore
CableDyn_FatalReport.f90 abnormal-end report of the driver (time reached)
CableDyn_Profile.f90 opt-in run-time profile of the driver (CABLEDYN_PROFILE)
cabledyn_fatal.c interrupt, fault and stack-overflow handlers of the driver

EI = 0 cable path:
Expand Down Expand Up @@ -493,8 +509,11 @@ import only Windows system DLLs.
minor extension 1 (`CableDyn_GetAbiMinor() ≥ 1`) adds in-process object queries
(object counts and ids, line node and segment values, point, body, and rod
states, and any output channel through `CableDyn_EvalChannel`), which return
what the matching output channel reports for the same state (see
[doc/capi.rst](doc/capi.rst)).
what the matching output channel reports for the same state. Minor extension 2
(`≥ 2`) adds the host-coupling calls: `CableDyn_InitDeckAt` (the statics solved
at the host's coupled-point positions), `CableDyn_SaveState` /
`CableDyn_RestoreState` (a one-slot deep copy of the model object for outer
correctors) and `CableDyn_GetCoupledLayout` (see [doc/capi.rst](doc/capi.rst)).
- **Python** (`python/cabledyn`): runs the driver, reads and post-processes
outputs, edits decks, runs studies, and binds the C interface through ctypes
with a pinned ABI version. With its object views and snapshots it is designed
Expand Down
98 changes: 96 additions & 2 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,101 @@ All notable changes to CableDyn are recorded in this file. The format follows
[Keep a Changelog](https://keepachangelog.com/en/1.1.0/) and the project uses
[Semantic Versioning](https://semver.org/spec/v2.0.0.html).

## [Unreleased]
## [0.2.0] - 2026-10-20

### Added

- Seabed friction in the static solve toward the as-laid position (`staticsFriction asLaid`,
with `layAzimuth` and `asLaidTension`), as in OrcaFlex. The default stays `none`, so existing
decks run as before. A 700 m chain on a 5° slope that the frictionless statics folds 24 m past
its anchor now holds where it was laid.
- Active tensioning (`CONTROL`) of finite-EI cables in OpenFAST, alone or in a deck with
`EI = 0` lines.
- Sub-stepping of tension-only (`EI = 0`) lines through fast segment rotation and slack-to-taut
snaps, on by default (`ei0_substeps auto|off`, `ei0_substep_angle`, `ei0_substep_max`).
It brings snap-load peaks at coarse time steps closer to converged runs; `off` restores the
previous results.
- Torsion of finite-EI lines in coupled OpenFAST (`CompMooring = 5`) and FAST.Farm runs.
- `Pinned` and `CoupledPinned`/`VesselPinned` rods in coupled OpenFAST runs.
- Seabed contact for `Free`/`Connect` points and `Point3` buoys: a heavy clump no longer sinks
through the seabed.
- Anchor uplift channels `AnchFz<L>`, `AnchFH<L>` and `TDP<L>Grd` for drag-anchor checks.
- C ABI 1 minor extension 2 for hosts that drive `Coupled` points (for example CFD solvers):
`CableDyn_InitDeckAt`, `CableDyn_SaveState`/`CableDyn_RestoreState` and
`CableDyn_GetCoupledLayout`, with matching Python methods. Existing functions are unchanged.
- `OutputRecovery equilibrium|element` option and the `CD_HermiteCable_Dyn_Curvature_Exact` and
`CD_HFMF_Curvature_Exact` functions (see Changed).
- Run-time profile of the standalone driver (`CABLEDYN_PROFILE=1`).
- New diagnostics, none of which changes results:
- run audit of `EI = 0` lines in the standalone driver: tension spikes, fast segment turns
and unresolved snaps, and a note for `rhoInf` above 0.95;
- a note when the static state of a finite-EI line is unstable out of its vertical plane;
- a note when the static layout of an `EI = 0` line folds back on the seabed, naming the
cause and the remedy;
- notes for a line stretched far beyond its elastic range and for a section too coarse for
its line;
- a warning when line nodes of a coupled OpenFAST run lie outside the SeaState
wave-kinematics grid.

### Changed

- Finite-EI node tension, curvature and bend moment (and `.t.out` segment tensions) are now
recovered from nodal equilibrium. On the lazy-wave example the largest tension error falls from
1552 N to 60 N on its former 87-element mesh, and oscillations near touchdown on a coarse mesh
are removed. End tensions and positions are unchanged. `OutputRecovery element` restores the
previous definitions.
- `EI = 0` lines step with a generalised-α force blend, as finite-EI lines do. Tension spikes of
lines that go slack are gone: a light cable under 3 m heave reported 4.2 MN where converged
runs give 0.093 MN. Tension statistics of the shipped examples change by at most 0.23 % (mean)
and 0.9 % (maximum). `False alpha_force_blend` selects the former scheme.
- Active tensioning of `EI = 0` lines follows MoorDyn-F through length ramps: fairlead tensions
within 0.13 % instead of up to 6.3 %. A command outside MoorDyn-F's bounds stops the run
instead of printing a warning, and the command acts on the segment at the host-driven
(fairlead-side) end, as in MoorDyn-F.
- In OpenFAST, a deck without `dtM` now solves every glue step (`dtM = DT`) instead of about
every 0.1 s, so the mooring loads reach the platform without delay. A deck `dtM` that is a
multiple of `DT` still trades this for speed (see Known issues).
- The touchdown point (`TDP<L>`) now moves continuously instead of in steps of one element.
- Finite-EI statics refine the mesh locally instead of as a whole, which cuts solve time (for
example 10.0 s to 0.33 s on a 462-element lazy wave). Decks that do not refine are unchanged.
- The power cable of `examples/iea15mw_umaine_mixed_cabledyn.dat` is re-meshed from 87 to 248
elements. Its static fairlead tension changes by 0.2 %.
- Faster runs: directional and multi-train wave kinematics (17 %), finite-EI cables clamped to
bodies or rods (66 %), and decks of `EI = 0` lines (13 %). Results can differ in the last digit
with the Intel compiler.
- The OpenFAST linearisation check and the FAST.Farm shared-mooring comparison against MoorDyn
are extended: per-fairlead stiffness agrees to 0.1 % (0.29 % for the transverse term) and
shared-mooring tension means to 0.02 %.

### Fixed

- Node output channels of a finite-EI line whose mesh the static solve refined now read the
deck node named, not the same index on the refined mesh.
- Static solves that failed or gave the wrong answer:
- creased gridded bathymetry (trenches, valleys) now has a static equilibrium;
- a finite-EI line over a rough, non-planar bathymetry no longer fails on a few centimetres
of roughness;
- a 3D finite-EI solve on a coarse mesh no longer stops with "unstable equilibrium";
- a finite-EI line with `ATTACHMENTS` in a cross current on a frictional seabed now solves.
- The anchor tension of a finite-EI cable laid on the seabed no longer jumps when the line
moves out of its plane.
- Explicit sub-stepping of free and pinned rods and Rigid6 bodies now accounts for seabed
contact, free-surface crossing and decks without lines, and seabed friction of rods and
bodies is applied implicitly (no more chatter on a frictional bed).
- `modified_newton` on `EI = 0` lines rebuilds the tangent as documented.
- Junction end tangent of a tension-only line step that ends right after a fresh tangent
evaluation.
- Error messages are no longer truncated, and now name the cause and workaround for neutral
buoyancy, unsupported couplings and anchors below the seabed.
- The development environment excludes OpenBLAS 0.3.34, which crashed the modal tests on some
AMD CPUs. Results are unchanged.

### Known issues

- In OpenFAST, a deck `dtM` larger than `DT` holds the loads between CableDyn's steps, so they
reach the platform about `dtM/2` late. The lag matters for stiff (taut or tension-leg)
moorings and for tension statistics; check such results at a smaller `dtM`. See the note on
the manual's OpenFAST page.

## [0.1.1] - 2026-10-09

Expand Down Expand Up @@ -440,6 +534,6 @@ Corrections made during the pre-release review.
values of the shipped example decks and states which tension (end element or
`FairTen` end force) each comparison uses.

[Unreleased]: https://github.com/SMI-Lab-Inha/CableDyn/compare/v0.1.1...HEAD
[0.2.0]: https://github.com/SMI-Lab-Inha/CableDyn/releases/tag/v0.2.0
[0.1.1]: https://github.com/SMI-Lab-Inha/CableDyn/releases/tag/v0.1.1
[0.1.0]: https://github.com/SMI-Lab-Inha/CableDyn/releases/tag/v0.1.0
4 changes: 2 additions & 2 deletions CITATION.cff
Original file line number Diff line number Diff line change
Expand Up @@ -22,8 +22,8 @@ authors:
repository-code: "https://github.com/SMI-Lab-Inha/CableDyn"
url: "https://github.com/SMI-Lab-Inha/CableDyn"
license: Apache-2.0
version: 0.1.1
date-released: 2026-10-09
version: 0.2.0
date-released: 2026-10-20
keywords:
- mooring dynamics
- cable dynamics
Expand Down
Loading
Loading