Repository navigation
validation: NDP 38 m high-mode riser VIV in uniform flow (L3-N) - #172
Merged
Merged
Conversation
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>
Owner
Author
|
@codex review |
Codex Review Summary: ✅ CompletedThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
|
Codex Review: Didn't find any major issues. Keep them coming! Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
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
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>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
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).
b1: the generic set of the Delta Flume caseand24b: Andersen et al. 2024b, cross-flow averageuls19: Ulveseter et al. 2019th16: Thorsen et al. 2016, fittedth16c:th16with Morison's linear CF damping keptResults (22 speeds, 200 elements, dt 1 ms)
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 belowand24b, 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.b1: σ/D CF within 2 %, but the frequency is a third high and the median strain 26 % high.th16andth16c: the damping form sets the frequency (0.193 against 0.153). Their strain errors are now nearly equal.Analysis choices
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.uls19.Convergence (
provenance.json)1.0 m/s:
uls19moves 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.
th16cby +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:
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:
th16moves most.Checks
pre-commiton the changed files.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.