Non-intrusive data-driven ROM framework for hemodynamics problems

Girfoglio, Michele; Scandurra, Leonardo; Ballarin, Francesco; Infantino, Giuseppe; Nicolò, Francesca; Montalto, Andrea; Rozza, Gianluigi; Scrofani, Roberto; Comisso, Marina; Musumeci, Francesco

doi:10.1007/s10409-021-01090-2

Cited by 15 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, a sensitivity study for EFR parameters α and χ for different meshes would give us a deeper insight into the performance of the solver. Finally, we are interested in practical cardiovascular applications, e.g., by extending to FSI the work carried out in [21,24].…”

Section: Discussionmentioning

confidence: 99%

Fluid-structure interaction simulations with a LES filtering approach in solids4Foam

Girfoglio¹,

Quaini²,

Rozza³

2021

Preprint

View full text Add to dashboard Cite

We consider the interaction of an incompressible fluid described by a Leray model with a hyperelastic structure modeled as a Saint Venant-Kirchhoff material. We focus on a strongly coupled, partitioned fluid-structure interaction (FSI) solver in a finite volume environment, combined with an arbitrary Lagrangian-Eulerian approach to deal with the motion of the fluid domain. The main novelty of this paper lies in applying a Leray model for the description of the flow field within a FSI context. For the implementation of the Leray model, which features a nonlinear differential low-pass filter, we adopt a three-step algorithm called Evolve-Filter-Relax. All the computational results presented in this article have been obtained with solids4Foam, the FSI toolbox developed for foam-extend, a branch of OpenFOAM. We validate our approach against numerical data available in the literature for the 3D cross flow past a cantilever beam at Reynolds number 100 and 400.

show abstract

Section: Discussionmentioning

confidence: 99%

Fluid-structure interaction simulations with a LES filtering approach in solids4Foam

Girfoglio¹,

Quaini²,

Rozza³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…p accuracy 70%25FFR calculation in coronary stenosis: case 2FFR 92%, min. p accuracy 90%Ballarin & Rozza [92]POD-GPfluid problem on moving domain—30stationary FSI of parameterised idealised valve—16unsteady FSI of parameterised channel—10Ballarin et al [82]POD-GPcoronary blood flow with varying physical and geometric parameters>99normal%100Ballarin et al [100]POD-GPcoronary blood flow with varying physical and geometric parameters>99normal%1530 b ; 100 b Han et al [101]POD-GPaneurysm blood flow with varying PI>95normal%2410Zainib et al [103]POD-GPcoronary artery bypass grafts>99normal%9 c Girfoglio et al [102]POD-Interpolation (RBF)aortic flow with LVAD p 99.5%, WSS 92.3%, u x 91.5%, u y 87.8%, u z 88.6%240Girfoglio et al [69]POD-Interpolation (RBF)aortic flow with LVAD: case 1 (PF 3.45 l min −1 ) p 99.8%, WSS 95.9%, u x 95.0%, u y 92.2%, u z 94.2%7 200 000aortic flow with LVAD: case 2 (PF 4.35 l min −1 ) p 99.5%, WSS 92.8%, u x 90.3%, u y 86.5%, u z 90.7%…”

Section: Reduced Order Modelling Of Vascular Flowmentioning

confidence: 99%

Accelerated simulation methodologies for computational vascular flow modelling

MacRaild,

Sarrami-Foroushani,

Lassila

et al. 2024

J. R. Soc. Interface.

View full text Add to dashboard Cite

Vascular flow modelling can improve our understanding of vascular pathologies and aid in developing safe and effective medical devices. Vascular flow models typically involve solving the nonlinear Navier–Stokes equations in complex anatomies and using physiological boundary conditions, often presenting a multi-physics and multi-scale computational problem to be solved. This leads to highly complex and expensive models that require excessive computational time. This review explores accelerated simulation methodologies, specifically focusing on computational vascular flow modelling. We review reduced order modelling (ROM) techniques like zero-/one-dimensional and modal decomposition-based ROMs and machine learning (ML) methods including ML-augmented ROMs, ML-based ROMs and physics-informed ML models. We discuss the applicability of each method to vascular flow acceleration and the effectiveness of the method in addressing domain-specific challenges. When available, we provide statistics on accuracy and speed-up factors for various applications related to vascular flow simulation acceleration. Our findings indicate that each type of model has strengths and limitations depending on the context. To accelerate real-world vascular flow problems, we propose future research on developing multi-scale acceleration methods capable of handling the significant geometric variability inherent to such problems.

show abstract

“…The technique used in this paper is data-driven or non-intrusive ROM, which allows us to build a reduced model without requiring the knowledge of the governing equations of the observed phenomenon. For this reason, this technique is suitable to deal with experimental data and it has been widely used in numerical simulations for industrial, naval, biomedical, and environmental applications [24][25][26][27][28][29][30].…”

Section: Model Order Reductionmentioning

confidence: 99%

Towards a Machine Learning Pipeline in Reduced Order Modelling for Inverse Problems: Neural Networks for Boundary Parametrization, Dimensionality Reduction and Solution Manifold Approximation

2023

View full text Add to dashboard Cite

In this work, we propose a model order reduction framework to deal with inverse problems in a non-intrusive setting. Inverse problems, especially in a partial differential equation context, require a huge computational load due to the iterative optimization process. To accelerate such a procedure, we apply a numerical pipeline that involves artificial neural networks to parametrize the boundary conditions of the problem in hand, compress the dimensionality of the (full-order) snapshots, and approximate the parametric solution manifold. It derives a general framework capable to provide an ad-hoc parametrization of the inlet boundary and quickly converges to the optimal solution thanks to model order reduction. We present in this contribution the results obtained by applying such methods to two different CFD test cases.

show abstract

Non-intrusive data-driven ROM framework for hemodynamics problems

Cited by 15 publications

References 27 publications

Fluid-structure interaction simulations with a LES filtering approach in solids4Foam

Fluid-structure interaction simulations with a LES filtering approach in solids4Foam

Accelerated simulation methodologies for computational vascular flow modelling

Towards a Machine Learning Pipeline in Reduced Order Modelling for Inverse Problems: Neural Networks for Boundary Parametrization, Dimensionality Reduction and Solution Manifold Approximation

Contact Info

Product

Resources

About