Deep learning of vortex-induced vibrations
From MaRDI portal
Publication:4647380
DOI10.1017/JFM.2018.872zbMATH Open1415.76177arXiv1808.08952OpenAlexW3105648287WikidataQ128705821 ScholiaQ128705821MaRDI QIDQ4647380FDOQ4647380
Authors: Maziar Raissi, M. S. Triantafyllou, Zhi-Cheng Wang, George Em Karniadakis 
Publication date: 15 January 2019
Published in: Journal of Fluid Mechanics (Search for Journal in Brave)
Abstract: Vortex induced vibrations of bluff bodies occur when the vortex shedding frequency is close to the natural frequency of the structure. Of interest is the prediction of the lift and drag forces on the structure given some limited and scattered information on the velocity field. This is an inverse problem that is not straightforward to solve using standard computational fluid dynamics (CFD) methods, especially since no information is provided for the pressure. An even greater challenge is to infer the lift and drag forces given some dye or smoke visualizations of the flow field. Here we employ deep neural networks that are extended to encode the incompressible Navier-Stokes equations coupled with the structure's dynamic motion equation. In the first case, given scattered data in space-time on the velocity field and the structure's motion, we use four coupled deep neural networks to infer very accurately the structural parameters, the entire time-dependent pressure field (with no prior training data), and reconstruct the velocity vector field and the structure's dynamic motion. In the second case, given scattered data in space-time on a concentration field only, we use five coupled deep neural networks to infer very accurately the vector velocity field and all other quantities of interest as before. This new paradigm of inference in fluid mechanics for coupled multi-physics problems enables velocity and pressure quantification from flow snapshots in small subdomains and can be exploited for flow control applications and also for system identification.
Full work available at URL: https://arxiv.org/abs/1808.08952
Recommendations
- Machine learning for vortex induced vibration in turbulent flow
- Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations
- Deep learning in fluid dynamics
- Physics-Driven Learning of the Steady Navier-Stokes Equations using Deep Convolutional Neural Networks
- Data-driven prediction of unsteady flow over a circular cylinder using deep learning
Fluid-solid interactions (including aero- and hydro-elasticity, porosity, etc.) (74F10) Vibrations in dynamical problems in solid mechanics (74H45) Viscous vortex flows (76D17)
Cites Work
- Gaussian processes for machine learning.
- Spectral/hp Element Methods for Computational Fluid Dynamics
- Bayesian numerical homogenization
- Multilayer feedforward networks are universal approximators
- Solving initial-boundary value problems for systems of partial differential equations using neural networks and optimization techniques
- V<scp>ORTEX</scp>-I<scp>NDUCED</scp> V<scp>IBRATIONS</scp>
- A direct numerical simulation study of flow past a freely vibrating cable
- A paradigm for data-driven predictive modeling using field inversion and machine learning
- Dynamics and flow structures in the turbulent wake of rigid and flexible cylinders subject to vortex-induced vibrations
- Inferring solutions of differential equations using noisy multi-fidelity data
- Brittleness of Bayesian inference under finite information in a continuous world
- Multifidelity information fusion algorithms for high-dimensional systems and massive data sets
- Neural network modeling for near wall turbulent flow.
- Vortex-induced vibrations of a long flexible cylinder in shear flow
- Hidden physics models: machine learning of nonlinear partial differential equations
- Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification
- Neural-net-induced Gaussian process regression for function approximation and PDE solution
- Data-driven forecasting of high-dimensional chaotic systems with long short-term memory networks
- Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
- Wavelet Scattering Regression of Quantum Chemical Energies
- Machine learning of linear differential equations using Gaussian processes
- Deep UQ: learning deep neural network surrogate models for high dimensional uncertainty quantification
- Numerical Gaussian Processes for Time-Dependent and Nonlinear Partial Differential Equations
- Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
- Title not available (Why is that?)
- Nonlinear information fusion algorithms for data-efficient multi-fidelity modelling
- Parametric Gaussian process regression for big data
Cited In (59)
- Dynamics of weighted flexible ribbons in a uniform flow
- PINN-FORM: a new physics-informed neural network for reliability analysis with partial differential equation
- Feature-adjacent multi-fidelity physics-informed machine learning for partial differential equations
- GFN: a graph feedforward network for resolution-invariant reduced operator learning in multifidelity applications
- Deep mixed residual method for solving PDE-constrained optimization problems
- Physics-informed deep learning for three-dimensional transient heat transfer analysis of functionally graded materials
- Physics-informed neural networks for the Reynolds-averaged Navier-Stokes modeling of Rayleigh-Taylor turbulent mixing
- Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data
- Physics-informed deep learning for simultaneous surrogate modeling and PDE-constrained optimization of an airfoil geometry
- The use of the Reynolds force vector in a physics informed machine learning approach for predictive turbulence modeling
- Learning Specialized Activation Functions for Physics-Informed Neural Networks
- Optimal control of PDEs using physics-informed neural networks
- DeepM\&Mnet: inferring the electroconvection multiphysics fields based on operator approximation by neural networks
- Physics-informed neural networks for inverse problems in supersonic flows
- General solutions for nonlinear differential equations: a rule-based self-learning approach using deep reinforcement learning
- High Reynolds number airfoil turbulence modeling method based on machine learning technique
- Embedding physical knowledge in deep neural networks for predicting the phonon dispersion curves of cellular metamaterials
- Deep neural networks for waves assisted by the Wiener–Hopf method
- An exploratory study on machine learning to couple numerical solutions of partial differential equations
- Bi-Orthogonal fPINN: A Physics-Informed Neural Network Method for Solving Time-Dependent Stochastic Fractional PDEs
- DPM: a deep learning PDE augmentation method with application to large-eddy simulation
- Non-intrusive reduced-order modeling using uncertainty-aware deep neural networks and proper orthogonal decomposition: application to flood modeling
- Physics-inspired architecture for neural network modeling of forces and torques in particle-laden flows
- Flows over periodic hills of parameterized geometries: a dataset for data-driven turbulence modeling from direct simulations
- Neural Networks with Local Converging Inputs (NNLCI) for Solving Conservation Laws, Part I: 1D Problems
- Discretizationnet: a machine-learning based solver for Navier-Stokes equations using finite volume discretization
- Error estimates for deep learning methods in fluid dynamics
- The linear-time-invariance notion of the Koopman analysis. Part 2. Dynamic Koopman modes, physics interpretations and phenomenological analysis of the prism wake
- Physics-informed semantic inpainting: application to geostatistical modeling
- NSFnets (Navier-Stokes flow nets): physics-informed neural networks for the incompressible Navier-Stokes equations
- Topology optimization based on deep representation learning (DRL) for compliance and stress-constrained design
- CAN-PINN: a fast physics-informed neural network based on coupled-automatic-numerical differentiation method
- PDE-constrained models with neural network terms: optimization and global convergence
- Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
- A vorticity-based criterion to characterise leading edge dynamic stall onset
- Neural Networks with Local Converging Inputs (NNLCI) for Solving Conservation Laws, Part II: 2D Problems
- Physics-informed PointNet: a deep learning solver for steady-state incompressible flows and thermal fields on multiple sets of irregular geometries
- Machine learning for vortex induced vibration in turbulent flow
- Physics and equality constrained artificial neural networks: application to forward and inverse problems with multi-fidelity data fusion
- Learning in Modal Space: Solving Time-Dependent Stochastic PDEs Using Physics-Informed Neural Networks
- On the risks of using double precision in numerical simulations of spatio-temporal chaos
- Error estimates and physics informed augmentation of neural networks for thermally coupled incompressible Navier Stokes equations
- ModalPINN: an extension of physics-informed neural networks with enforced truncated Fourier decomposition for periodic flow reconstruction using a limited number of imperfect sensors
- Physics constrained learning for data-driven inverse modeling from sparse observations
- Neural vortex method: from finite Lagrangian particles to infinite dimensional Eulerian dynamics
- PhyCRNet: physics-informed convolutional-recurrent network for solving spatiotemporal PDEs
- Investigating and Mitigating Failure Modes in Physics-Informed Neural Networks (PINNs)
- Microstructure-informed probability-driven point-particle model for hydrodynamic forces and torques in particle-laden flows
- Monte Carlo fPINNs: deep learning method for forward and inverse problems involving high dimensional fractional partial differential equations
- Prediction of turbulent heat transfer using convolutional neural networks
- INN: interfaced neural networks as an accessible meshless approach for solving interface PDE problems
- Reinforcement-learning-based control of confined cylinder wakes with stability analyses
- Kernel functions embed into the autoencoder to identify the sparse models of nonlinear dynamics
- A highly accurate strategy for data-driven turbulence modeling
- PhyGeoNet: physics-informed geometry-adaptive convolutional neural networks for solving parameterized steady-state PDEs on irregular domain
- When and why PINNs fail to train: a neural tangent kernel perspective
- Extended Physics-Informed Neural Networks (XPINNs): A Generalized Space-Time Domain Decomposition Based Deep Learning Framework for Nonlinear Partial Differential Equations
- Dynamics of a rigid-flexible coupling system in a uniform flow
- Nonlinear dynamics and control of galloping vibration under unsteady wind flow by high-frequency excitation
Uses Software
This page was built for publication: Deep learning of vortex-induced vibrations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4647380)
