Repository navigation
fix: a finite-EI dynamic step on the inertia's round-off floor converges - #168
Merged
Merged
Conversation
A finite-EI cable could fail its first dynamic step at a small time step: Newton stagnated just above the tolerance, and the step recovery's smaller steps only raised it. Found on a 13 m riser (64 elements) at rest in a 0.95 m/s current taking the VIV lift at dtM 1.25e-4 s: the residual stopped at 1.06 times the tolerance, and each 4-fold smaller substep raised the stagnant residual about 16-fold (3.8e-8, 6.2e-7, 8.6e-6, 1.3e-4, 2.6e-3, 4.7e-2 N), to 3.4e4 times the tolerance at 1024 substeps. The 16-fold growth per 4-fold step is the inertia's 1/dt^2, not the 1/dt of a velocity-coupled force (drag, VIV lift): the inertia takes the acceleration (q - q_n)/(beta dt^2) - ... from coordinates stored to their last bits, so its residual cannot be settled below about eps sum_j |M_ij| |q_j| / (beta dt^2). The rows that stalled were the axial rows of nodes 8.5 to 12 m deep, not the cross-flow rows the lift loads: the Newton correction they needed, a few 1e-16 m, is below the 1.8e-15 m spacing of those coordinates. Without the lift the step starts at the static equilibrium and converges at its predictor; with it the line near rest sets no inertial force scale, and tol times the force scale (here its axial round-off floor) lies below the inertia's floor. A floor of the force scale built from that bound, where it binds, would accept residuals up to 16 times the bound, some 60 times the floor Newton reaches (the bound sits about 4 times above it: 1.7e-7 against 3.8e-8 N on the riser, 4.7e-3 against 1.2e-3 N in the test below). The fix is therefore a stall test, as on the EI = 0 route: when no step length of a fresh Newton correction reduces the residual, the residual is below 1e-4 of the force scale, and the correction moves no free coordinate by more than 16 eps times its scale (the largest coordinate magnitude or element length; 1 or the largest tangent or twist magnitude for those DOFs), the iterate is converged. The riser now runs at dtM 1.25e-4 s, and over 2 s its node positions and fairlead tension continue the time-step sequence of dtM 5e-4 and 2.5e-4 s (differences 1.3 mm and 0.55 mm, 5.5 N and 2.9 N). A step that meets the tolerance is unchanged: every example and test-data deck gives bit-identical outputs on the old and new driver (229 files over 118 decks), and through the C API five coupled steps of every deck give bit-identical line arrays (1685 arrays over 70 decks), and the full test suite (424 tests) passes on the default and the Prescott OpenBLAS kernel, where the 66 example decks also run with no fallback note. Test: test_hermite_viv round-off floor, the test's 100 m line hung vertically from 50 to 150 m depth, from rest with the lift at dt 2.5e-5 s. Before, the first step stagnated at 2.4 times the tolerance through its 50-iteration budget and failed; now each step stops on the floor after two iterations, and the cross-flow displacement at 0.02 s matches the same line's at dt 1e-3 s within 1 % (to 5 digits). 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. 🚀 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". |
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
A finite-EI cable could fail its first dynamic step at a small time step: Newton stagnated just above the tolerance, and the step recovery's smaller substeps only made it worse. The fix is a stall test on the finite-EI route, like the one the EI = 0 route already has. A step that meets the tolerance is unchanged; every example and test deck gives bit-identical output.
How it was found
The Delta Flume riser (64 elements, 13 m, at rest in a 0.95 m/s current, VIV lift on) at$\Delta t_M = 1.25\times10^{-4}$ s. The residual stopped at 1.06 times the tolerance, and every 4-fold smaller substep raised the stagnant residual about 16-fold:
Cause
The 16-fold growth per 4-fold step is the$1/\Delta t^2$ of the inertia, not the $1/\Delta t$ of a velocity-coupled force such as drag or the VIV lift. The inertia takes the acceleration $(q - q_n)/(\beta\Delta t^2) - \dots$ from coordinates stored to their last bits, so its residual cannot be settled below
Fix
The iterate is accepted as converged when all of these hold:
Results
Riser: now runs at$\Delta t_M = 1.25\times10^{-4}$ s. Over 2 s its node positions and fairlead tension continue the sequence of $5\times10^{-4}$ and $2.5\times10^{-4}$ s:
New test$\Delta t = 2.5\times10^{-5}$ s.
test_hermite_viv(round-off floor): the test's 100 m line hung vertically from 50 to 150 m depth, from rest with the lift atChecks