Repository navigation
fix: the coupled VIV response converges at second order in the time step - #171
Conversation
A taut line locked in by the synchronisation model changed its lock-in frequency by 0.74 %, 0.41 % and 0.27 % per halving of the step from 25 to 200 steps per cycle (the long-run VIV checks), worse than first order, while the same phase update under prescribed motion was second order. The phase sampled the committed generalised-alpha acceleration a_n for its cross-flow phase (and the wake oscillator for its forcing). That acceleration is the line's at t_n + (alpha_m - alpha_f) dt only, a first-order error at rho_inf < 1, and at rho_inf = 1 it carries an undamped alternating mode of the integrator: on the 20 m line the mid-span a_n alternated by +-11 m/s^2 against a physical acceleration of about 1.3 m/s^2. The lock-in at rho_inf = 1 therefore converged to a frequency 3.4 % low (3.940 at 3200 steps per cycle against 4.0797 rad/s), and at rho_inf 0.8 and 0.4 it was first order (0.06/n and 0.25/n at n steps per response period). Prescribed motion imposes the exact acceleration, which is why it did not show there. Candidates switched off one at a time on that line, 25 to 3200 steps per cycle: a second-order running mean square (exact exponential with trapezoidal samples) changed nothing; a fixed normalisation in place of the RMS left it first order; a tighter Newton tolerance changed nothing; the lift at a fixed shedding rate (no phase feedback) was second order (ratios 3.8 to 4.0); the acceleration recomputed from the equations of motion after every step moved the limit to 4.0797 rad/s; and the phase on the step's mid-point motion with the acceleration from the converged velocities restored second order (ratios 3.6 to 5.0, then 4.01 to 4.04 from 400 steps on) at rho_inf 1 and 0.8 alike. No amplitude table, flow frame or in-line VIV is involved in that case. The phase now advances by the implicit mid-point rule, one fixed-point pass, on the node's cross-flow motion at the step's mid-point: the mean position, the velocity (q_n+1 - q_n)/dt and the acceleration (v_n+1 - v_n)/dt, the step means of the velocity and of its derivative (second order at every rho_inf, free of the committed acceleration's lag and alternating mode, and keeping the phase of a harmonic motion exactly). The step's lift takes the phase predicted with the rate of the previous step's mid-point, a new row of the VIV motion statistics (two with in-line VIV), so the step recovery, sub-step slots, snapshots and checkpoints carry it and a restart stays bit-identical; a newly installed VIV model seeds it from the present state. The running mean squares advance by the mid-point rule (1 - exp(-dt/T_w) on the mid-point sample), the in-line phase in the same way slaved to the mid-point cross-flow rate, the flow frame's and the wake filter's filtered velocities exactly for the velocity linear over the step, and the wake oscillator under the mid-point acceleration (held over the step, its integral exact) at the mean of the start and end wake frequencies, that acceleration being its predictor (row 2 of its statistics). The time discretisation of the VIV phase therefore changes on purpose; this is not a round-off change. Measured on the same line from 25 to 3200 steps per cycle (EI = 0 line and rho_inf 0.8 unless noted), the ratio of successive changes per halving of the step, before and after: frequency, rho_inf 1: limit 3.4 % low; 3.6-4.9 frequency, rho_inf 0.8 / 0.4: 2.0-3.4 / 1.5-3.2; 3.6-4.8 / 3.8-4.5 mid-span A/D, in-line VIV: 2.2-2.3; 2.6-4.3 frequency, flow frame: 1.6-2.0; 3.1-4.5 frequency, amplitude table: 1.9-2.3; 3.0-4.5 wake oscillator, frequency: 2.0-2.5; 3.8-4.0 finite-EI cable, frequency: 1.7-2.3; 3.1-4.1 The Richardson limits at rho_inf 1, 0.8 and 0.4 agree to 1e-9 (4.0797304 rad/s), and the errors are about 2.2/n^2 (rho_inf 1, 0.8) and 3.4/n^2 (0.4) in frequency and 1.6/n^2 and 3.4/n^2 in mid-span A/D at n steps per response period, 3.5/n^2 on the finite-EI cable. With the cable seeded at its static stretch, rho_inf 1 reaches the rho_inf 0.8 limit; from unit tangents the undamped tangent-stretch mode rings and moves it at fine steps (the seed, not the VIV update). Under prescribed motion the phase error of the long-run check after 400 cycles at 100 steps per cycle is 0.0167 rad against 0.0334 before, still second order (3.99). The energy closure of that check at 100 steps per cycle is 2.0e-4 of the VIV work against 8.3e-5 before, second order (ratio 4.0): the lift's predicted phase now takes the rate of the previous step's mid-point, half a step behind the old step-start rate. The two VIV example decks change at their default dtM 0.02 s (about 170 steps per response period, rhoInf 0.4) and move toward their results at dtM 0.00125 s. viv_taut_line_crossflow, against dtM 0.00125 s: the mid-span RMS 0.31 % high before, 0.02 % low after; the lock-in frequency 0.15 % low before, 0.018 % after; the fairlead tension RMS 0.29 % high before, 0.027 % low after. viv_taut_cable_inline: the quarter-span in-line RMS 1.56 % low before, 0.34 % after; the cross-flow frequency 0.10 % high before, 0.022 % after; the largest fairlead tension 0.70 % high before, 0.23 % low after; the mid-span RMS 0.21 % and 0.20 % low. Over the 90 s the phase moves, so the time series differ pointwise by up to 12 % (crossflow, fairlead tension) and 36 % (inline, quarter-span y) of the channel's range. Every other example and test-data deck (132 decks) gives bit-identical output files and console logs. The full test suite (427 tests) passes on the default and the Prescott OpenBLAS kernel, and the 66 example decks run with no fallback note on both. Test: viv_step_order, the lock-in frequency of the line second order from 100 to 400 steps per cycle at rho_inf 1 (ratio 3.99) and 0.4 (3.67) and within 1e-4 of each other (4.3e-5), the wake oscillator's crossing frequency (3.90) and the finite-EI cable from 200 to 800 steps per cycle (4.39); on the previous code every check fails (ratios 2.44, 2.27, 2.18 and 2.76, the two rho_inf 3.1 % apart). The VIV state layouts in test_model, test_system, test_viv_coupled, test_hermite_viv_frame and test_hfmf_mirror carry the predictor rows. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
…the VIV update With the mid-point VIV update the predictor check of the lifted taut line fails one cell, rho_inf 1 at 25 steps per cycle (21 per response period): from the unit-tangent seed z max/D 0.5903 against the balanced seed's 0.5641 (+4.6 %) and Es max 1.51 times it. Every step converges (6.15 iterations on average, at most 21). At rho_inf 1 nothing damps the unit seed's stretch ringing, and at that resolution it leaves a near-Nyquist velocity in the trajectory: the mid-node (v_n+1 - v_n)/dt alternates by 4.8 m/s^2 against a VIV acceleration of 3.2 m/s^2 (a velocity of about 0.09 m/s, 27 % of the VIV velocity; the committed a_n alternates by 32 against 17, 19 against 10.5 on the old update), 10 to 20 times less at 50 steps per cycle. The response then depends on how the VIV update treats that velocity: four equally consistent variants (the last two mid-point accelerations averaged, a three-point second-order Nyquist-free acceleration, an averaged predictor rate, both of the latter) give z max/D 0.623, 0.579, 0.589 and 0.578, +0.8 % to +10 % from the converged 0.5639 with the old update's +0.8 % among them. That value is the fine-step one (200 to 800 steps per cycle), the same at rho_inf 0.8 with either seed and at rho_inf 1 with the balanced seed. The new update reaches it from 50 steps per cycle with either seed (unit seed 0.5632 at 50, 0.5641 at 100, 0.5639 from 200 on), while the old update settled at rho_inf 1 0.23 % high from the unit seed and 0.1 % low from the balanced one. The result is deterministic (Newton tolerance 1e-6 to 1e-10 and a 1e-7 seed tilt change it by under 0.03 %). So that cell measures the VIV update's treatment of an unresolved spurious velocity, not the predictor. It keeps G1 (every step converges) and G4 (iterations) and skips G2 and G3, and a new gate G7 holds the convergence claim: the unit seed at rho_inf 1 and 50 steps per cycle within 0.5 % of the converged z max/D 0.5639 (measured 0.5632). The other cells keep G2 and G3 (measured at most 1.07 times and 0.09 %). doc/theory.rst and the CHANGELOG note that at rho_inf 1 from an unbalanced seed the VIV response is resolution-sensitive below about 50 steps per cycle: keep rhoInf at or below 0.95 or seed the tangents at the stretch. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
…phase The nine cases and their sensitivity runs (half the time step, 128 elements, 80 s for cases 5, 6, 8 and 9, the 38.1 kN/m top spring) rerun on the second-order VIV phase update. The counts are unchanged: the dominant mode right in 5 of 9 and within one in all, the mean in-line displacement within 17 % in 7 of 9 (-25 % to +34 %). The cross-flow amplitude is -45 % to +4 % against the maxima (-40 % to +18 % against the envelopes; within the 12 % measurement scatter in cases 2, 4, 6 and 7), the cross-flow curvature -39 % to +26 %, the in-line curvature -53 % to +111 %. Half the time step now changes the peak amplitude of cases 1-4, 7 and 8 by at most 2.7 % (4.5 % before) and their in-line curvature by at most 1.2 % (10 % before). Case 5 keeps its peak amplitude within 0.6 % (it moved by up to 20 % before) while its in-line curvature moves by up to 25 %. The peak amplitude of case 6 now depends on the step and the mesh: -11 % at half the time step, kept over an 80 s run, and -13 % with 128 elements, its other metrics within 2 % (in-line curvature 12 %). Case 9 still settles in mode 7 at half the time step. README, provenance.json (new 80 s runs of cases 6 and 8 at both steps), summary.json, response_comparison.csv, VALIDATION.md and the changelog entry follow. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@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 it up! 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". |
…int phase The mid-point VIV phase update changes every coupled-VIV result, so the validation case L3-W and the numbers the documents quote from coupled VIV runs are recomputed with it, each as its text describes (deck, options, window, output flag). L3-W (validation/experiments/wang_scr), rerun as its README says, and its two sensitivity runs: the largest r.m.s. strain over the measured largest 1.0729 -> 1.0733, the station mean 1.0362 -> 1.0361, the r.m.s. log error 0.339 -> 0.338, the dominant frequency 0.992 Hz (unchanged), 7 r.m.s. peaks along the span (unchanged); 400 elements 1.0753 -> 1.0759 and half the time step 1.0742 -> 1.0747 (0.24 % and 0.13 % from the base run). Every number and sentence of the README, VALIDATION.md and the CHANGELOG still holds at its printed precision; summary.json, the comparison CSV and provenance.json (commit, date, sensitivity) are updated. Numbers changed: - doc/outputs.rst, examples/viv_taut_cable_inline.dat: the VIV loads' power over 60-90 s 8.52 -> 8.45 W, the drag (and damping) 8.56 -> 8.48 W (balance within 0.5 %, unchanged). - doc/python_postprocessing.rst: the travelling-wave index 0.05 -> 0.04. - doc/theory.rst: the EI = 0 wake-oscillator line locks in at 0.283 Hz (was "the same 0.282 Hz"); the amplitude estimate within 0.04 % (0.1 % on the EI = 0 line; was 0.03 %); Thorsen's damping A/D 1.02 -> 1.01; the moving/held pipe table (peak 0.819/0.819 -> 0.811/0.818, RMS 0.446/0.447 -> 0.446/0.446; without the row 0.711/0.850 -> 0.700/0.851 and 0.349/0.450 -> 0.345/0.450; Cl alone 0.713/0.714 -> 0.713/0.712 and 0.372/0.371 -> 0.372/0.370; without 0.711/0.736 -> 0.700/0.733 and 0.349/0.375 -> 0.345/0.374), the RMS agreement within 0.2 % -> 0.6 % (0.02 % with the table); the towed cable 0.7905 / 0.7906 -> 0.7902 / 0.7903, 0.665 -> 0.663, 0.6764 / 0.6764 -> 0.6758 / 0.6758, Tf on the held cable at most 0.23 % -> 0.24 %. - doc/driver_format.md: towed within 0.01 % -> 0.02 %, at most 0.23 % -> 0.24 %. - VALIDATION.md: L2-VIV zero seed 0.701 -> 0.699 against 0.699; L2-VIV-EI 0.662/0.421 against 0.663/0.421 -> 0.661/0.420 against 0.661/0.420; the coupled VIV row 0.6645 / 0.6646 -> 0.6631 / 0.6625 (standalone 0.665 -> 0.663). The L2-VIV band against MoorDyn-F, rerun over 150-300 s at U 0.06-0.42 m/s: mode 1 at 0.09-0.18 m/s within 0.2 %, mode 3 at 0.39-0.42 m/s within 1.4 %, and at 0.36 m/s MoorDyn-F settles in mode 2 and CableDyn in mode 3 (the earlier phase update gives the same branches, its A/D within 0.5 % of the new one at every speed, so the discrepancy predates this change); the row said "mode 3 at U >= 0.36 m/s within 1.2 %". - CHANGELOG.md: the wake entry's EI = 0 frequency, the amplitude estimate 0.03 % -> 0.04 %, the frame entry's pipe and tow numbers as in the theory, and the #169 entry's largest A/D within 0.75 % -> 0.1 % except at rho_inf 1 and 25 steps per cycle. - tests/test_viv_frame_deck.f90 and tests/test_hermite_viv_frame.f90 (header comments only): the measured values of their gates. Every other quoted coupled-VIV number still holds at its precision (the example decks' A/D 0.66, 0.82, 0.19 and 0.03, their frequencies, the in-line and higher-harmonic gates, the wake, diameter and Thorsen gates, the riser case). The Delta Flume case was rerun before; the NDP case is on another branch. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@codex review |
|
Codex Review: Didn't find any major issues. Hooray! 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". |
…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>
The OD 48 mm research cable of the FLOTANT tests at MARIN (de Wilde, Heijnsdijk & de Ridder 2021, Deliverable D5.5, MARIN report 30995-53-DWB): 6.4 m hanging from the carriage with a 200 kg clump, towed at the 40 speeds of 0.025-1.0 m/s. It tests cross-flow and in-line VIV of a real cable section against three published coefficient sets, none fitted to these tests, on a structure identified only from the specimen's forced-oscillation RAOs. validation/experiments/flotant/flotant_viv.py writes a deck per case, runs them in parallel (reused when deck and executable are unchanged) and compares: - tow: A/D_rms = sigma/OD at 1/2L, 3/4L and L, cross-flow and in line, at the same test speed, the model's displacement processed as the report's accelerometer motions (the g theta/omega^2 tilt term, the 3.5 rad/s high-pass); Ur with f1 1.77 Hz as Appendix 3; 60 s runs, statistics after 20 s, dt 2 ms; - rao: the in-air (5 and 10 mm) and in-water (5 mm) RAOs of Appendices 1 and 2, the structural check. The line follows the report's FEM tables node by node, in fresh water (Table 2-2 implies 1000 kg/m^3), with the clump or counterweight as a 20 kN/m axial spring in series. What the tests leave open is identified from the RAOs: cable EI 1650 N m^2 and bending damping 130 N m^2 s from the in-air resonance (the tables' EI 3000 needs MARIN's empirical factor 1.10), and in water a link chain bending with EI 100 N m^2 and the clump held laterally by 32.5 kN/m and 20 N s/m, which give the measured split of the first in-water mode (r.m.s. log error 0.46 in surge against 1.19 for MARIN's fixed clump and 1.17 for a free one). Sets, checked against the articles: - 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 the NDP riser: blind here; - 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, VIV DAMPING 0 0 1): blind; - wake, Facchinetti et al. (2004) (CL0 0.3, St 0.2, eps 0.3, A 12): blind. Result on the second-order VIV phase update (#171) (cross-flow r.m.s. log error over the three stations, Ur >= 3): - uls19 0.731: the first peak at 1/2L is 0.755 at Ur 5.30 against 0.776 at 5.58, but the rise starts at a lower speed (0.42 against 0.18 at Ur 3.53), the lock-in releases at Ur 7.06 against 5.88 (1.2 Ur late) and the upper branch stays at 0.64-0.71 above Ur 9 where the test falls to 0.18-0.44; - b1 0.594: 38 % low at the peak (0.483), releases at the measured Ur; - wake 1.208: 62 % low (0.296). With MARIN's fixed clump or a free clump (End B Free) uls19 scores 0.721 and 0.692 but releases at Ur 8.83 and 9.12 and misses the RAOs. extract_d55.py reads the data from the report's PDF (FEM tables from the text, the RAO charts from the vector graphics, Appendix 3 from the raster images calibrated on the grid lines; every point maps to a tested speed within 0.0085 m/s). The caveats of the data are stated: the Ur basis (1.77 Hz against the 1.3 Hz first in-water mode of Sec. 5.3), the bottom tension (1436 N in Table 6-1 against about 1700 N in the FEM table) and the towing direction alternating with speed. Half the time step, two elements per table element and 120 s runs change no A/D_rms by more than 0.006 at five speeds; the RAO scores move by at most 0.001. The default command run into a new work directory reproduces the committed record byte for byte. Added to VALIDATION.md as L3-F, to the experiments index, the changelog and the references (de Wilde et al. 2021, from the report's PDF; no DOI); the top-level README now names the seven published experiments. flotant_viv.py and ndp_riser_viv.py now remove a folder's result, executable stamp and output before writing new inputs, so a rerun that fails or is interrupted cannot leave the previous model's result to be reused; a tow selection entirely below Ur 3 prints n/a for its scores instead of failing before the comparison files are written. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
…17) (#179) An optional VIV STOCHASTIC section, rows TypeName sigma c [Nf [seed]], makes the centre cF of a line type's synchronisation band the slowly varying random process of Ulveseter, Thorsen, Saevik & Larsen (2017, Eq. 6 and Fig. 4): F0 = cF + sum_i a sin(p_i + 2 pi f_i theta), theta = integral U/D dt, Nf components (default 100) at the mid-points f_i = (i - 1/2) c cF/Nf of a flat spectrum over (0, c cF], amplitude a = sigma sqrt(2/Nf), so F0 has the mean cF and the standard deviation sigma. Each component advances at its non-dimensional frequency times U/D, as the shedding phase does (U the shedding speed of the phase rate). The start phases are uniform on [0, 2 pi), drawn per node from a minimal-standard stream that the seed, the node and the line select: the nodes are independent, as in the article, a run repeats its realisation and two lines of one type differ. The band half-width dF stays constant. theta is the one new state: one more row of each node's VIV motion statistics, so step recovery, snapshots, rollback and checkpoints (standalone and the OpenFAST mirror) carry it; the phases are rebuilt from the seed. The step advances theta by dt U/D at the mid-point and takes F0 at theta + dt U/(2D), the mid-point rule of the phase (#171). On EI = 0 lines and finite-EI cables, standalone and coupled, with or without in-line VIV; refused on a type without Cl > 0 or with a WAKE OSCILLATOR row. Checks (test_viv_stochastic, test_viv_coupled): - the process with the article's NDP values (cF 0.144, sigma 0.016, c 0.07, 100 components) over theta 0-4e6 has the mean cF to 2e-6, the standard deviation sigma to four digits and an excess kurtosis of -0.18; the phases repeat per seed and node and differ between them; - a sigma 0 row is the deck without it, bit for bit, on both cores; - with sigma 0.02 a run repeats bit for bit, another seed differs, and the taut cable stays locked in (A/D within 1 % of the constant centre's over 50-80 s on both cores); - the coupled checkpoint restart continues bit for bit with theta in both VIV blocks (one more value per node), a rebuild without the VIV state does not, and a rewound step repeats; - refusals: no Cl, a wake-oscillator type, c out of (0, 1], a non-integer Nf, a seed out of range. The EI = 0 model's explicit copy and move routines and its VIV row count (CD_Model_VIV_NMS) carry the new fields. Python reader and builder: the section, its native checks and a round trip. Driver format, theory (Stochastic band centre), capabilities, changelog and the reference (from the article's first page). Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
Summary
The coupled VIV response converged at first order or worse in the time step. Under prescribed motion, the same phase update was second order. The cause is that the synchronisation model read the line's acceleration from the generalised-α committed value$a_n$ , and that is not the line's acceleration. The phase now advances on the step's mid-point motion, and every coupled VIV variant converges at second order. The limits at $\rho_\infty$ 1, 0.8 and 0.4 agree to 1e-9.
This is a deliberate change to the VIV time discretisation, not a round-off change. Only the two VIV example decks change, and both move toward their fine-step results.
How it was found
A taut line locked in by the synchronisation model (the long-run VIV checks) changed its lock-in frequency by 0.74 %, 0.41 % and 0.27 % per halving of the step, from 25 to 200 steps per cycle.
Cause
The phase sampled$a_n$ for its cross-flow phase, and the wake oscillator used it for its forcing.
Prescribed motion imposes the exact acceleration, which is why it did not show there.
Candidates switched off one at a time on that line, from 25 to 3200 steps per cycle, over 400 cycles:
No amplitude table, flow frame or in-line VIV is involved in that case.
Fix
Phase: the implicit mid-point rule with one fixed-point pass. It uses the node's cross-flow motion at the step's mid-point:
This pair is second order at every$\rho_\infty$ , free of the lag and the alternating mode, and keeps the phase of a harmonic motion exactly.
Lift predictor: the step's lift takes the phase predicted with the previous step's mid-point rate.
Other updates:
Validators: the FMF and model restore checks accept the signed predictor rows.
Docs: the scheme, the measured error constants and the recommended steps per period are in
doc/theory.rst, with a CHANGELOG "Fixed" entry.Results
Ratio of successive changes per halving of the step (4 is second order), from 25 to 3200 steps per cycle:
Error constants at$n$ steps per response period:
Long-run check under prescribed motion:
Example decks
Both VIV example decks are at their default
dtM0.02 s (about 170 steps per response period,rhoInf0.4). Each value is the error against the same deck atdtM0.00125 s:viv_taut_line_crossflow, mid-span RMSviv_taut_line_crossflow, lock-in frequencyviv_taut_line_crossflow, fairlead tension RMSviv_taut_cable_inline, quarter-span in-line RMSviv_taut_cable_inline, cross-flow frequencyviv_taut_cable_inline, largest fairlead tensionOver the 90 s the phase moves, so the time series differ pointwise by up to 12 % (crossflow, fairlead tension) and 36 % (inline, quarter-span y) of the channel's range.
Delta Flume validation case (L3-D) rerun
The nine cases and every sensitivity run were rerun on this update; the recorded results, README,
provenance.json,VALIDATION.mdand the changelog entry follow.Against the measurements:
Convergence (half the time step, 128 elements, 80 s runs):
The 80 s runs of cases 6 and 8 at both steps are new;
provenance.jsonrecords them.Wang SCR case (L3-W) rerun and every quoted VIV number rechecked
L3-W: rerun with its two sensitivity runs. Every printed number and sentence still holds at its precision:
summary.json, the comparison CSV andprovenance.jsonare updated.Quoted numbers: every number in the docs, VALIDATION.md, CHANGELOG, example comments and test headers that comes from coupled VIV was recomputed from the deck, window and output it describes. The ones that moved at their printed precision are updated:
outputs.rst: the VIV power balance, 8.52 → 8.45 W;python_postprocessing.rst: the travelling-wave index, 0.05 → 0.04;theory.rst: the wake lock-in, the amplitude-estimate tracking, Thorsen's damping, and the frame pipe and tow tables;driver_format.md;Claims already wrong on dev, now corrected:
viv_lockingates and is unchanged.Test
tests/test_viv_step_order.f90(ctestviv_step_order, 30 s):The VIV state layouts in
test_model,test_system,test_viv_coupled,test_hermite_viv_frameandtest_hfmf_mirrorcarry the predictor rows.The tangent-predictor test of #169 at$\rho_\infty = 1$ and 25 steps per cycle
On top of #169, one cell of$\rho_\infty = 1$ and 25 steps per cycle, seeded with unit tangents. Every step still converges (G1) within the iteration budget (G4). But its largest mid-span displacement is 4.7 % above the converged value (limit 2 %), and its strain energy is 1.51 times the reference (limit 1.5).
hermite_tangent_predictorchanges. It is the lifted line atCause. With no numerical damping, the seed's undamped tangent-stretch ringing leaves a near-Nyquist velocity of about 27 % of the VIV velocity at 21 steps per response period. Both the old and the new update feed it into the phase.
What that cell measures. It measures how an update treats that spurious velocity, not the predictor. Four equally consistent second-order variants (different filters of the sign-flipping component) land +0.8 % to +10 % from the converged z max/D of 0.5639, and the deviation is insensitive to the Newton tolerance and to a seed tilt.
z max/D over 20 cycles; the converged value is 0.5639:
doc/theory.rstand the CHANGELOG state that atrhoInf≤ 0.95, asdoc/options.rstalready advises, or seed the tangents at the stretch.Checks
All on the branch rebased on dev 4b94321 (#169, #170):
pre-commit.