physics.flu-dyn

arXiv:2501.06933v1 Announce Type: new Abstract: We introduce Neural Discrete Equilibrium (NeurDE), a machine learning (ML) approach for long-term forecasting of flow phenomena that relies on a "lifting" of physical conservation laws into the framework of kinetic theory. The kinetic formulation provides an excellent structure for ML algorithms by separating nonlinear, non-local physics into a nonlinear but local relaxation to equilibrium and a linear non-local transport. This separation allows the ML to focus on the local nonlinear components while addressing the simpler linear transport with efficient classical numerical algorithms. To accomplish this, we design an operator network that maps macroscopic observables to equilibrium states in a manner that maximizes entropy, yielding expressive BGK-type collisions. By incorporating our surrogate equilibrium into the lattice Boltzmann (LB) algorithm, we achieve accurate flow forecasts for a wide range of challenging flows. We show that NeurDE enables accurate prediction of compressible flows, including supersonic flows, while tracking shocks over hundreds of time steps, using a small velocity lattice-a heretofore unattainable feat without expensive numerical root finding.

arXiv:2409.12483v2 Announce Type: replace-cross Abstract: Numerical methods of the ADER family, in particular finite-element ADER-DG and finite-volume ADER-WENO methods, are among the most accurate numerical methods for solving quasilinear PDE systems. The internal structure of ADER-DG and ADER-WENO numerical methods contains a large number of basic linear algebra operations related to matrix multiplications. The main interface of software libraries for matrix multiplications for high-performance computing is BLAS. This paper presents an effective method for integration the standard functions of the BLAS interface into the implementation of these numerical methods. The calculated matrices are small matrices; at the same time, the proposed implementation makes it possible to effectively use existing JIT technologies. The proposed approach immediately operates on AoS, which makes it possible to efficiently calculate flux, source and non-conservative terms without need to carry out transposition. The obtained computational costs demonstrated that the effective implementation, based on the use of the JIT functions of the BLAS, outperformed both the implementation based on the general BLAS functions and the vanilla implementations by several orders of magnitude. At the same time, the complexity of developing an implementation based on the approach proposed in this work does not exceed the complexity of developing a vanilla implementation.

arXiv:2309.04755v2 Announce Type: replace Abstract: Ultrafast ultrasound blood flow imaging is a state-of-the-art technique for depiction of complex blood flow dynamics in vivo through thousands of full-view image data (or, timestamps) acquired per second. Physics-informed Neural Network (PINN) is one of the most preeminent solvers of the Navier-Stokes equations, widely used as the governing equation of blood flow. However, that current approaches rely on full Navier-Stokes equations is impractical for ultrafast ultrasound. We hereby propose a novel PINN training framework for solving the Navier-Stokes equations. It involves discretizing Navier-Stokes equations into steady state and sequentially solving them with test-time adaptation. The novel training framework is coined as SeqPINN. Upon its success, we propose a parallel training scheme for all timestamps based on averaged constant stochastic gradient descent as initialization. Uncertainty estimation through Stochastic Weight Averaging Gaussian is then used as an indicator of generalizability of the initialization. This algorithm, named SP-PINN, further expedites training of PINN while achieving comparable accuracy with SeqPINN. The performance of SeqPINN and SP-PINN was evaluated through finite-element simulations and in vitro phantoms of single-branch and trifurcate blood vessels. Results show that both algorithms were manyfold faster than the original design of PINN, while respectively achieving Root Mean Square Errors of 0.63 cm/s and 0.81 cm/s on the straight vessel and 1.35 cm/s and 1.63 cm/s on the trifurcate vessel when recovering blood flow velocities. The successful implementation of SeqPINN and SP-PINN open the gate for real-time training of PINN for Navier-Stokes equations and subsequently reliable imaging-based blood flow assessment in clinical practice.

arXiv:2501.06466v1 Announce Type: cross Abstract: This work introduces a novel application for predicting the macroscopic intrinsic permeability tensor in deformable porous media, using a limited set of micro-CT images of real microgeometries. The primary goal is to develop an efficient, machine-learning (ML)-based method that overcomes the limitations of traditional permeability estimation techniques, which often rely on time-consuming experiments or computationally expensive fluid dynamics simulations. The novelty of this work lies in leveraging Convolutional Neural Networks (CNN) to predict pore-fluid flow behavior under deformation and anisotropic flow conditions. Particularly, the described approach employs binarized CT images of porous micro-structure as inputs to predict the symmetric second-order permeability tensor, a critical parameter in continuum porous media flow modeling. The methodology comprises four key steps: (1) constructing a dataset of CT images from Bentheim sandstone at different volumetric strain levels; (2) performing pore-scale simulations of single-phase flow using the lattice Boltzmann method (LBM) to generate permeability data; (3) training the CNN model with the processed CT images as inputs and permeability tensors as outputs; and (4) exploring techniques to improve model generalization, including data augmentation and alternative CNN architectures. Examples are provided to demonstrate the CNN's capability to accurately predict the permeability tensor, a crucial parameter in various disciplines such as geotechnical engineering, hydrology, and material science. An exemplary source code is made available for interested readers.

arXiv:2501.03933v1 Announce Type: new Abstract: Numerical stabilization techniques are often employed in under-resolved simulations of convection-dominated flows to improve accuracy and mitigate spurious oscillations. Specifically, the Evolve-Filter-Relax (EFR) algorithm is a framework which consists in evolving the solution, applying a filtering step to remove high-frequency noise, and relaxing through a convex combination of filtered and original solutions. The stability and accuracy of the EFR solution strongly depend on two parameters, the filter radius $\delta$ and the relaxation parameter $\chi$. Standard choices for these parameters are usually fixed in time, and related to the full order model setting, i.e., the grid size for $\delta$ and the time step for $\chi$. This paper makes two significant improvements to the standard EFR framework by proposing: (i) time-dependent parameters, (ii) data-driven adaptive optimization of the parameters in time, considering a fully-resolved simulation as a reference. In particular, we propose three different classes of Optimized-EFR strategies, aiming to optimize one or both parameters. Moreover, we investigate the accuracy and efficiency of the proposed optimization algorithms considering different objective functions, both local (point-valued) and global (such as the kinetic energy). The new Optimized-EFR strategies are tested in the under-resolved simulation of a turbulent flow past a cylinder at $Re=1000$. The new Optimized-EFR results are more accurate than the standard EFR solution while maintaining a similar computational time. In particular, we show that using a global objective function and including the $H^1$ velocity seminorm is crucial to accurately match the reference flow dynamics.

arXiv:2501.03286v1 Announce Type: new Abstract: Hull form designing is an iterative process wherein the performance of the hull form needs to be checked via computational fluid dynamics calculations or model experiments. The stern shape has to undergo a process wherein the hull form variations from the pressure distribution analysis results are repeated until the resistance and propulsion efficiency meet the design requirements. In this study, the designer designed a pressure distribution that meets the design requirements; this paper proposes an inverse design algorithm that estimates the stern shape using deep learning. A convolutional neural network was used to extract the features of the pressure distribution expressed as a contour, whereas a multi-task learning model was used to estimate various sections of the stern shape. We estimated the stern shape indirectly by estimating the control point of the B-spline and comparing the actual and converted offsets for each section; the performance was verified, and an inverse design is proposed herein

arXiv:2311.10872v3 Announce Type: replace-cross Abstract: Since viscoelastic two-phase flows arise in various industrial and natural processes, developing accurate and efficient software for their detailed numerical simulation is a highly relevant and challenging research task. We present a geometrical unstructured Volume-of-Fluid (VOF) method for handling two-phase flows with viscoelastic liquid phase, where the latter is modeled via generic rate-type constitutive equations and a one-field description is derived by conditional volume averaging of the local instantaneous bulk equations and interface jump conditions. The method builds on the plicRDF-isoAdvector geometrical VOF solver that is extended and combined with the modular framework DeboRheo for viscoelastic computational fluid dynamics (CFD). A piecewise-linear geometrical interface reconstruction technique on general unstructured meshes is employed for discretizing the viscoelastic stresses across the fluid interface. DeboRheo facilitates a flexible combination of different rheological models with appropriate stabilization methods to address the high Weissenberg number problem.

arXiv:2501.03406v1 Announce Type: new Abstract: This paper presents a novel machine-learning framework for reconstructing low-order gust-encounter flow field and lift coefficients from sparse, noisy surface pressure measurements. Our study thoroughly investigates the time-varying response of sensors to gust-airfoil interactions, uncovering valuable insights into optimal sensor placement. To address uncertainties in deep learning predictions, we implement probabilistic regression strategies to model both epistemic and aleatoric uncertainties. Epistemic uncertainty, reflecting the model's confidence in its predictions, is modeled using Monte Carlo dropout, as an approximation to the variational inference in the Bayesian framework, treating the neural network as a stochastic entity. On the other hand, aleatoric uncertainty, arising from noisy input measurements, is captured via learned statistical parameters, which propagates measurement noise through the network into the final predictions. Our results showcase the efficacy of this dual uncertainty quantification strategy in accurately predicting aerodynamic behavior under extreme conditions while maintaining computational efficiency, underscoring its potential to improve online sensor-based flow estimation in real-world applications.

arXiv:2501.03300v1 Announce Type: new Abstract: Artificial intelligence (AI) for fluid mechanics has become attractive topic. High-fidelity data is one of most critical issues for the successful applications of AI in fluid mechanics, however, it is expensively obtained or even inaccessible. This study proposes a high-efficient data forward generation method from the partial differential equations (PDEs). Specifically, the solutions of the PDEs are first generated either following a random field (e.g. Gaussian random field, GRF, computational complexity O(NlogN), N is the number of spatial points) or physical laws (e.g. a kind of spectra, computational complexity O(NM), M is the number of modes), then the source terms, boundary conditions and initial conditions are computed to satisfy PDEs. Thus, the data pairs of source terms, boundary conditions and initial conditions with corresponding solutions of PDEs can be constructed. A Poisson neural network (Poisson-NN) embedded in projection method and a wavelet transform convolutional neuro network (WTCNN) embedded in multigrid numerical simulation for solving incompressible Navier-Stokes equations is respectively proposed. The feasibility of generated data for training Poisson-NN and WTCNN is validated. The results indicate that even without any DNS data, the generated data can train these two models with excellent generalization and accuracy. The data following physical laws can significantly improve the convergence rate, generalization and accuracy than that generated following GRF.

arXiv:2501.01934v1 Announce Type: new Abstract: Designing re-entry vehicles requires accurate predictions of hypersonic flow around their geometry. Rapid prediction of such flows can revolutionize vehicle design, particularly for morphing geometries. We evaluate advanced neural operator models such as Deep Operator Networks (DeepONet), parameter-conditioned U-Net, Fourier Neural Operator (FNO), and MeshGraphNet, with the objective of addressing the challenge of learning geometry-dependent hypersonic flow fields with limited data. Specifically, we compare the performance of these models for two grid types: uniform Cartesian and irregular grids. To train these models, we use 36 unique elliptic geometries for generating high-fidelity simulations with a high-order entropy-stable DGSEM solver, emphasizing the challenge of working with a scarce dataset. We evaluate and compare the four operator-based models for their efficacy in predicting hypersonic flow field around the elliptic body. Moreover, we develop a novel framework, called Fusion DeepONet, which leverages neural field concepts and generalizes effectively across varying geometries. Despite the scarcity of training data, Fusion DeepONet achieves performance comparable to parameter-conditioned U-Net on uniform grids while it outperforms MeshGraphNet and vanilla DeepONet on irregular, arbitrary grids. Fusion DeepONet requires significantly fewer trainable parameters as compared to U-Net, MeshGraphNet, and FNO, making it computationally efficient. We also analyze the basis functions of the Fusion DeepONet model using Singular Value Decomposition. This analysis reveals that Fusion DeepONet generalizes effectively to unseen solutions and adapts to varying geometries and grid points, demonstrating its robustness in scenarios with limited training data.

arXiv:2501.01453v1 Announce Type: new Abstract: Rapid yet accurate simulations of fluid dynamics around complex geometries is critical in a variety of engineering and scientific applications, including aerodynamics and biomedical flows. However, while scientific machine learning (SciML) has shown promise, most studies are constrained to simple geometries, leaving complex, real-world scenarios underexplored. This study addresses this gap by benchmarking diverse SciML models, including neural operators and vision transformer-based foundation models, for fluid flow prediction over intricate geometries. Using a high-fidelity dataset of steady-state flows across various geometries, we evaluate the impact of geometric representations -- Signed Distance Fields (SDF) and binary masks -- on model accuracy, scalability, and generalization. Central to this effort is the introduction of a novel, unified scoring framework that integrates metrics for global accuracy, boundary layer fidelity, and physical consistency to enable a robust, comparative evaluation of model performance. Our findings demonstrate that foundation models significantly outperform neural operators, particularly in data-limited scenarios, and that SDF representations yield superior results with sufficient training data. Despite these advancements, all models struggle with out-of-distribution generalization, highlighting a critical challenge for future SciML applications. By advancing both evaluation methodologies and modeling capabilities, this work paves the way for robust and scalable ML solutions for fluid dynamics across complex geometries.

arXiv:2411.05631v2 Announce Type: replace-cross Abstract: Computational cardiovascular flow modeling plays a crucial role in understanding blood flow dynamics. While 3D models provide acute details, they are computationally expensive, especially with fluid-structure interaction (FSI) simulations. 1D models offer a computationally efficient alternative, by simplifying the 3D Navier-Stokes equations through axisymmetric flow assumption and cross-sectional averaging. However, traditional 1D models based on finite element methods (FEM) often lack accuracy compared to 3D averaged solutions. This study introduces a novel physics-constrained machine learning technique that enhances the accuracy of 1D blood flow models while maintaining computational efficiency. Our approach, utilizing a physics-constrained coupled neural differential equation (PCNDE) framework, demonstrates superior performance compared to conventional FEM-based 1D models across a wide range of inlet boundary condition waveforms and stenosis blockage ratios. A key innovation lies in the spatial formulation of the momentum conservation equation, departing from the traditional temporal approach and capitalizing on the inherent temporal periodicity of blood flow. This spatial neural differential equation formulation switches space and time and overcomes issues related to coupling stability and smoothness, while simplifying boundary condition implementation. The model accurately captures flow rate, area, and pressure variations for unseen waveforms and geometries. We evaluate the model's robustness to input noise and explore the loss landscapes associated with the inclusion of different physics terms. This advanced 1D modeling technique offers promising potential for rapid cardiovascular simulations, achieving computational efficiency and accuracy. By combining the strengths of physics-based and data-driven modeling, this approach enables fast and accurate cardiovascular simulations.

arXiv:2501.00556v1 Announce Type: cross Abstract: This research employs Universal Differential Equations (UDEs) alongside differentiable physics to model viscoelastic fluids, merging conventional differential equations, neural networks and numerical methods to reconstruct missing terms in constitutive models. This study focuses on analyzing four viscoelastic models: Upper Convected Maxwell (UCM), Johnson-Segalman, Giesekus, and Exponential Phan-Thien-Tanner (ePTT), through the use of synthetic datasets. The methodology was tested across different experimental conditions, including oscillatory and startup flows. While the UDE framework effectively predicts shear and normal stresses for most models, it demonstrates some limitations when applied to the ePTT model. The findings underscore the potential of UDEs in fluid mechanics while identifying critical areas for methodological improvement. Also, a model distillation approach was employed to extract simplified models from complex ones, emphasizing the versatility and robustness of UDEs in rheological modeling.

arXiv:2501.00037v1 Announce Type: cross Abstract: Several numerical simulations of a co-axial particle-laden swirling air flow in a vertical circular pipe were performed. The air flow was modeled using the unsteady Favre-averaged Navier-Stokes equations. A Lagrangian model was used for the particle motion. The gas and particles are coupled through two-way momentum exchange. The results of the simulations using three versions of the k-epsilon turbulence model (standard, re-normalization group (RNG), and realizable) are compared with experimental mean velocity profiles. The standard model achieved the best overall performance. The realizable model was unable to satisfactorily predict the radial velocity; it is also the most computationally-expensive model. The simulations using the RNG model predicted additional recirculation zones. We also compared the particle and parcel approaches in solving the particle motion. In the latter, multiple similar particles are grouped in a single parcel, thereby reducing the amount of computation.

arXiv:2501.00450v1 Announce Type: cross Abstract: This work presents an overview of mesh-induced errors commonly experienced by cell-centred finite volumes (CCFV), for which the face-centred finite volume (FCFV) paradigm offers competitive solutions. In particular, a robust FCFV solver for incompressible laminar flows is integrated in OpenFOAM and tested on a set of steady-state and transient benchmarks. The method outperforms standard simpleFoam and pimpleFoam algorithms in terms of optimal convergence, accuracy, stability, and robustness. Special attention is devoted to motivate and numerically demonstrate the ability of the FCFV method to treat non-orthogonal, stretched, and skewed meshes, where CCFV schemes exhibit shortcomings.

arXiv:2501.00143v1 Announce Type: cross Abstract: This paper presents the application of the Shifted Boundary Method (SBM) to thermal flow simulations, utilizing incomplete octree meshes (Octree-SBM) to perform multiphysics simulations that couple flow and heat transfer. By employing a linearized form of the Navier-Stokes equations, we accelerate the simulations while maintaining accuracy. SBM enables precise enforcement of field and derivative boundary conditions on intercepted elements, allowing for accurate flux calculations near complex geometries, when using non-boundary fitted meshes. Both Dirichlet and Neumann boundary conditions are implemented within the SBM framework, with results demonstrating that SBM ensures precise enforcement of Neumann boundary conditions on octree-based meshes. We illustrate this approach by simulating flows across different regimes, benchmarking results over several orders of magnitude variation in Rayleigh numbers ($Ra \sim 10^3$ to $10^9$) and Reynolds numbers ($Re \sim 10^0$ to $10^4$), covering laminar, transitional, and turbulent regimes. Coupled thermal-flow phenomena as well as summary statistics across all these regimes are accurately captured without any additional numerical treatments, beyond a Residual-based Variational Multiscale formulation (RB-VMS). This approach offers a reliable and efficient solution for complex geometries, boundary conditions and flow regimes in computational multiphysics simulations.

arXiv:2412.10748v2 Announce Type: replace Abstract: Simulating fuel sloshing within aircraft tanks during flight is crucial for aircraft safety research. Traditional methods based on Navier-Stokes equations are computationally expensive. In this paper, we treat fluid motion as point cloud transformation and propose the first neural network method specifically designed for simulating fuel sloshing in aircraft. This model is also the deep learning model that is the first to be capable of stably modeling fluid particle dynamics in such complex scenarios. Our triangle feature fusion design achieves an optimal balance among fluid dynamics modeling, momentum conservation constraints, and global stability control. Additionally, we constructed the Fueltank dataset, the first dataset for aircraft fuel surface sloshing. It comprises 320,000 frames across four typical tank types and covers a wide range of flight maneuvers, including multi-directional rotations. We conducted comprehensive experiments on both our dataset and the take-off scenario of the aircraft. Compared to existing neural network-based fluid simulation algorithms, we significantly enhanced accuracy while maintaining high computational speed. Compared to traditional SPH methods, our speed improved approximately 10 times. Furthermore, compared to traditional fluid simulation software such as Flow3D, our computation speed increased by more than 300 times.

arXiv:2412.16787v1 Announce Type: new Abstract: Hamilton's equations are fundamental for modeling complex physical systems, where preserving key properties such as energy and momentum is crucial for reliable long-term simulations. Geometric integrators are widely used for this purpose, but neural network-based methods that incorporate these principles remain underexplored. This work introduces SympFlow, a time-dependent symplectic neural network designed using parameterized Hamiltonian flow maps. This design allows for backward error analysis and ensures the preservation of the symplectic structure. SympFlow allows for two key applications: (i) providing a time-continuous symplectic approximation of the exact flow of a Hamiltonian system--purely based on the differential equations it satisfies, and (ii) approximating the flow map of an unknown Hamiltonian system relying on trajectory data. We demonstrate the effectiveness of SympFlow on diverse problems, including chaotic and dissipative systems, showing improved energy conservation compared to general-purpose numerical methods and accurate

arXiv:2412.17146v1 Announce Type: new Abstract: Significant advances have been achieved in leveraging foundation models, such as large language models (LLMs), to accelerate complex scientific workflows. In this work we introduce FoamPilot, a proof-of-concept LLM agent designed to enhance the usability of FireFOAM, a specialized solver for fire dynamics and fire suppression simulations built using OpenFOAM, a popular open-source toolbox for computational fluid dynamics (CFD). FoamPilot provides three core functionalities: code insight, case configuration and simulation evaluation. Code insight is an alternative to traditional keyword searching leveraging retrieval-augmented generation (RAG) and aims to enable efficient navigation and summarization of the FireFOAM source code for developers and experienced users. For case configuration, the agent interprets user requests in natural language and aims to modify existing simulation setups accordingly to support intermediate users. FoamPilot's job execution functionality seeks to manage the submission and execution of simulations in high-performance computing (HPC) environments and provide preliminary analysis of simulation results to support less experienced users. Promising results were achieved for each functionality, particularly for simple tasks, and opportunities were identified for significant further improvement for more complex tasks. The integration of these functionalities into a single LLM agent is a step aimed at accelerating the simulation workflow for engineers and scientists employing FireFOAM for complex simulations critical for improving fire safety.

arXiv:2412.15408v1 Announce Type: new Abstract: In the class of immersed boundary (IB) methods, the choice of the delta function plays a crucial role in transferring information between fluid and solid domains. Most prior work has used isotropic kernels that do not preserve the divergence-free condition of the velocity field, leading to loss of incompressibility of the solid when interpolating velocity to Lagrangian markers. To address this issue, in simulations involving large deformations of incompressible hyperelastic structures immersed in fluid, researchers often use stabilization approaches such as adding a volumetric energy term. Composite B-spline (CBS) kernels offer an alternative by maintaining the discrete divergence-free property. This work evaluates CBS kernels in terms of volume conservation and accuracy, comparing them with isotropic kernel functions using a construction introduced by Peskin (IB kernels) and B-spline (BS) kernels. Benchmark tests include pressure-loaded and shear-dominated flows, such as an elastic band under pressure loads, a pressurized membrane, a compressed block, Cook's membrane, and a slanted channel flow. Additionally, we validate our methodology using a complex fluid-structure interaction model of bioprosthetic heart valve dynamics. Results demonstrate that CBS kernels achieve superior volume conservation compared to isotropic kernels, eliminating the need for stabilization techniques. Further, CBS kernels converge on coarser fluid grids, while IB and BS kernels need finer grids for comparable accuracy. Unlike IB and BS kernels, which perform better with larger mesh ratios, CBS kernels improve with smaller mesh ratios. Wider kernels provide more accurate results across all methods, but CBS kernels are less sensitive to grid spacing variations than isotropic kernels.