The FDA nozzle benchmark: “In theory there is no difference between theory and practice, but in practice there is”

Abstract

The utility of flow simulations relies on the robustness of computational fluid dynamics (CFD) solvers and reproducibility of results. The aim of this study was to validate the Oasis CFD solver against in vitro experimental measurements of jet breakdown location from the FDA nozzle benchmark at Reynolds number 3500, which is in the particularly challenging transitional regime. Simulations were performed on meshes consisting of 5, 10, 17, and 28 million (M) tetrahedra, with Δt = 10 seconds. The 5M and 10M simulation jets broke down in reasonable agreement with the experiments. However, the 17M and 28M simulation jets broke down further downstream. But which of our simulations are "correct"? From a theoretical point of view, they are all wrong because the jet should not break down in the absence of disturbances. The geometry is axisymmetric with no geometrical features that can generate angular velocities. A stable flow was supported by linear stability analysis. From a physical point of view, a finite amount of "noise" will always be present in experiments, which lowers transition point. To replicate noise numerically, we prescribed minor random angular velocities (approximately 0.31%), much smaller than the reported flow asymmetry (approximately 3%) and model accuracy (approximately 1%), at the inlet of the 17M simulation, which shifted the jet breakdown location closer to the measurements. Hence, the high-resolution simulations and "noise" experiment can potentially explain discrepancies in transition between sometimes "sterile" CFD and inherently noisy "ground truth" experiments. Thus, we have shown that numerical simulations can agree with experiments, but for the wrong reasons.

The effect of turbulence on transitional flow in theFDA's benchmark nozzle model using large‐eddy simulation

“…The use of inlet disturbances in this work supports the findings from previous studies 22,23,27 ; that adding artificial disturbances helps to stabilise numerical simulation, making it robust to time-step selection, and that mean characteristics are insensitive to these disturbances throughout the model, even in laminar regions. This is the first study to assess the effects of numerical inlet disturbances on turbulence statistics.…”

“…19 In numerical simulation the addition of inlet disturbances reduces sensitivities and stabilises jet breakdown location; this has been observed in the current and previous studies. 22,23,27 Clearly, disturbances bring about very different effects in the experiment and LES simulation. It is likely that the LES overpredicts turbulence values in regions that would otherwise be laminar if inlet disturbances were not applied.…”

“…Subsequently, scale resolving simulations were conducted using large-eddy simulation (LES) and direct numerical simulation (DNS) methodologies. [21][22][23][24][25][26][27] Studies which considered the transitional regime 21,23,24 used variants of LES or DNS, and more accurately matched PIV data. Delorme et al 24 adopted a hybrid LES-immersed boundary method and found that velocity profiles agreed well with PIV data at the presented locations, with numerical viscous shear stresses overestimated.…”

“…They hypothesised that adding turbulence intensity to the inlet added energy to the flow, stabilising the jet and thus reducing jet breakdown location to better match experimental data. Bergersen et al 27 found that adding noise to the inlet of the model at the same Reynolds number also caused their jet to break down sooner. Without noise, their jet broke down later than the experimental data.…”

A framework for automated and objective modification of tubular structures: Application to the internal carotid artery

“…To investigate the flow, we used Oasis , an open‐source, second‐order energy‐conserving and minimally dissipative CFD solver, previously used for biomedical applications and is verified and validated . We assumed the blood to behave as a Newtonian fluid with a kinematic viscosity of ν = 0.0035 m 2 /second.…”