☆ 4.7 Article

A hybrid reduced-order model combing deep learning for unsteady flow

PHYSICS OF FLUIDS (2022)

Related references

Note: Only part of the references are listed.

Review Mechanics

Dynamic Mode Decomposition and Its Variants

Peter J. Schmid

Summary: Dynamic mode decomposition (DMD) is a technique for factorization and dimensionality reduction of data sequences, which simplifies complex evolution processes to their dominant features and essential components. It has been widely applied in various fields beyond fluid dynamics as well.

ANNUAL REVIEW OF FLUID MECHANICS (2022)

Add to Collection

Article Engineering, Multidisciplinary

POD-DL-ROM: Enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition

Stefania Fresca et al.

Summary: DL-ROMs are proposed to overcome limitations of conventional ROMs, but require expensive training. The proposed method combines POD and multi-fidelity pretraining to avoid the costly training stage of DL-ROMs.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2022)

Add to Collection

Article Mathematics, Applied

Low-Rank Dynamic Mode Decomposition: An Exact and Tractable Solution

Patrick Heas et al.

Summary: This work focuses on the linear approximation of high-dimensional dynamical systems using low-rank dynamic mode decomposition. It demonstrates the existence of a closed-form solution for the non-convex low-rank constrained optimization problem and proposes low-complexity algorithms for building reduced models. Numerical simulations using synthetic and physical data benchmarks validate the effectiveness of the algorithms.

JOURNAL OF NONLINEAR SCIENCE (2022)

Add to Collection

Article Engineering, Multidisciplinary

Unsteady flow prediction from sparse measurements by compressed sensing reduced order modeling

Xinshuai Zhang et al.

Summary: This study proposes a novel compressed sensing reduced-order modeling framework for predicting unsteady flow fields from sparse and noisy sensor measurements. The framework includes an offline learning stage using Long Short Term Memory (LSTM) model and sparsity-promoting Dynamic Mode Decomposition (DMD) algorithm, and an online forecasting stage using Deep Neural Network (DNN) to establish correlations and predict flow fields accurately.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2022)

Add to Collection

Article Engineering, Aerospace

Unsteady aerodynamic reduced-order modeling based on machine learning across multiple airfoils

Kai Li et al.

Summary: In this study, an efficient and accurate reduced-order model for unsteady aerodynamics considering the variation of airfoil geometry is constructed using a long short-term memory (LSTM) network. The model is validated with NACA 6-series airfoils in transonic flow, demonstrating its capability to accurately capture unsteady aerodynamics for varying shape parameters. Finally, the constructed ROM is applied to uncertainty and sensitivity analysis with respect to the variation of geometry parameters.

AEROSPACE SCIENCE AND TECHNOLOGY (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Non-intrusive reduced-order modeling using uncertainty-aware Deep Neural Networks and Proper Orthogonal Decomposition: Application to flood modeling

Pierre Jacquier et al.

Summary: Deep Learning research is rapidly growing and can bring benefits to older fields like Computational Fluid Dynamics. This study compares methods for uncertainty quantification in Deep Neural Networks and applies them to engineering problems.

JOURNAL OF COMPUTATIONAL PHYSICS (2021)

Add to Collection

Article Mechanics

Assessment of unsteady flow predictions using hybrid deep learning based reduced-order models

Sandeep Reddy Bukka et al.

Summary: This paper introduces two deep learning-based hybrid data-driven reduced-order models for predicting unsteady fluid flows. The first model (POD-RNN) projects time series data to a low-dimensional space, while the second model (CRAN) extracts low-dimensional features using convolutional neural networks. Through benchmark problems, it is found that the CRAN model outperforms the POD-RNN model in complex flow scenarios.

PHYSICS OF FLUIDS (2021)

Add to Collection

Article Engineering, Aerospace

Efficient prediction of transonic flutter boundaries for varying Mach number and angle of attack via LSTM network

Wencheng Li et al.

Summary: The article introduces a new method for transonic aeroelastic analysis using aerodynamic reduced-order modeling and deep learning methods, which can efficiently predict unsteady aerodynamic responses and flutter boundaries of aircraft under different flight parameters.

AEROSPACE SCIENCE AND TECHNOLOGY (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Randomized Dynamic Mode Decomposition for Oscillation Modal Analysis

Abdullah Alassaf et al.

Summary: This research aims to analyze oscillation modes from PMU measurement data using dynamic mode decomposition, and improves the accuracy and efficiency of system eigenvalue identification through data stacking and randomization techniques.

IEEE TRANSACTIONS ON POWER SYSTEMS (2021)

Add to Collection

Article Mechanics

Reduced order model for nonlinear multi-directional ocean wave propagation

Sandeep Reddy Bukka et al.

Summary: This paper introduces a reduced order model (ROM) for the propagation of nonlinear multi-directional ocean wave-fields, which can achieve real-time computation and shows significant improvement for short-crested waves.

PHYSICS OF FLUIDS (2021)

Add to Collection

Article Mechanics

Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders

Romit Maulik et al.

Summary: This study demonstrates that using a combination of convolutional autoencoders (CAEs) and recurrent neural networks effectively overcomes the limitations of the POD-Galerkin technique in advection-dominated nonlinear PDEs. Truncated systems with only a few latent space dimensions can accurately reproduce complex fluid dynamics phenomena, and parameter information can be easily embedded to detect trends in system evolution.

PHYSICS OF FLUIDS (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

A novel ensemble-based conceptual-data-driven approach for improved streamflow simulations

Anna E. Sikorska-Senoner et al.

Summary: A novel ensemble-based conceptual-data-driven approach (CDDA) was developed to correct the residuals from hydrological model (HM) simulations using a data-driven model (DDM), showing improvement in streamflow simulation. Tests on three Swiss catchments demonstrated an increase of 16-29% in mean continuous ranked probability score compared to standalone HM, with XGB and RF performing the best and recommended for simulating HM residuals.

ENVIRONMENTAL MODELLING & SOFTWARE (2021)

Add to Collection

Review Mechanics

On closures for reduced order models-A spectrum of first-principle to machine-learned avenues

Shady E. Ahmed et al.

Summary: Reduced order models (ROMs) have been a fundamental discipline of theoretical fluid mechanics for over a century, evolving from early mathematical models and Galerkin models to the innovative data-driven modeling approach. The impact of data-driven modeling, artificial intelligence, and machine learning has significantly changed the standard ROM methodology over the last two decades. The development of ROM closures, which aim to model the effect of discarded ROM modes in under-resolved simulations, demonstrates the ongoing reshaping of the field of reduced order modeling through state-of-the-art data-driven modeling techniques.

PHYSICS OF FLUIDS (2021)

Add to Collection

Article Mechanics

Flow prediction using dynamic mode decomposition with time-delay embedding based on local measurement

Yuan Yuan et al.

Summary: A method for flow field prediction based on local PIV measurement with time-delay embedding is developed. The DMD with time-delay embedding improves both spatial and temporal resolution of flow field prediction, showing high accuracy and robustness to noise.

PHYSICS OF FLUIDS (2021)

Add to Collection

Review Engineering, Aerospace

Data-driven modeling for unsteady aerodynamics and aeroelasticity

Jiaqing Kou et al.

Summary: Aerodynamic modeling plays a crucial role in unstable aerodynamics, with traditional methods restricted by theoretical and empirical research. Data-driven methods offer high accuracy, low computational cost, and great potential for flow control and engineering optimization.

PROGRESS IN AEROSPACE SCIENCES (2021)

Add to Collection

Review Mechanics

Machine Learning for Fluid Mechanics

Steven L. Brunton et al.

ANNUAL REVIEW OF FLUID MECHANICS, VOL 52 (2020)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Accelerating the convergence of steady adjoint equations by dynamic mode decomposition

Wengang Chen et al.

STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION (2020)

Add to Collection

Article Mechanics

Deep neural networks for nonlinear model order reduction of unsteady flows

Hamidreza Eivazi et al.

PHYSICS OF FLUIDS (2020)

Add to Collection

Article Engineering, Aerospace

A transition prediction method for flow over airfoils based on high-order dynamic mode decomposition

Mengmeng Wu et al.

CHINESE JOURNAL OF AERONAUTICS (2019)

Add to Collection

Review Engineering, Aerospace

Non-intrusive reduced-order modeling for fluid problems: A brief review

Jian Yu et al.

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART G-JOURNAL OF AEROSPACE ENGINEERING (2019)

Add to Collection

Article Mechanics

Dynamic mode decomposition with exogenous input for data-driven modeling of unsteady flows

Jiaqing Kou et al.

PHYSICS OF FLUIDS (2019)

Add to Collection

Article Mechanics

Time-resolved turbulent velocity field reconstruction using a long short-term memory (LSTM)-based artificial intelligence framework

Zhiwen Deng et al.

PHYSICS OF FLUIDS (2019)

Add to Collection

Article Mechanics

Spectral proper orthogonal decomposition and its relationship to dynamic mode decomposition and resolvent analysis

Aaron Towne et al.

JOURNAL OF FLUID MECHANICS (2018)

Add to Collection

Article Mechanics

Snapshot POD analysis of transient flow in the pilot stage of a jet pipe servo valve

Lin Wu et al.

JOURNAL OF TURBULENCE (2018)

Add to Collection

Article Automation & Control Systems

A method to construct reduced-order parameter-varying models

Jennifer Annoni et al.

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL (2017)

Add to Collection

Article Engineering, Mechanical

Experimental Investigation on the Time-Space Evolution of a Laminar Separation Bubble by Proper Orthogonal Decomposition and Dynamic Mode Decomposition

D. Lengani et al.

JOURNAL OF TURBOMACHINERY-TRANSACTIONS OF THE ASME (2017)

Add to Collection

Article Mechanics

An improved criterion to select dominant modes from dynamic mode decomposition

Jiaqing Kou et al.

EUROPEAN JOURNAL OF MECHANICS B-FLUIDS (2017)

Add to Collection

Article Mechanics

The lowest Reynolds number of vortex-induced vibrations

Jiaqing Kou et al.

PHYSICS OF FLUIDS (2017)

Add to Collection

Article Mechanics

Higher order dynamic mode decomposition to identify and extrapolate flow patterns

Soledad Le Clainche et al.

PHYSICS OF FLUIDS (2017)

Add to Collection

Article Mechanics

Reduced-order analysis of buffet flow of space launchers

Vladimir Statnikov et al.

JOURNAL OF FLUID MECHANICS (2017)

Add to Collection

Article Computer Science, Interdisciplinary Applications

A non-intrusive acceleration technique for compressible flow solvers based on dynamic mode decomposition

N. Andersson

COMPUTERS & FLUIDS (2016)

Add to Collection

Article Mathematics, Applied

Dynamic Mode Decomposition with Control

Joshua L. Proctor et al.

SIAM JOURNAL ON APPLIED DYNAMICAL SYSTEMS (2016)

Add to Collection

Article Mathematics, Applied

A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition

Matthew O. Williams et al.

JOURNAL OF NONLINEAR SCIENCE (2015)

Add to Collection

Article Mechanics

Parametrized data-driven decomposition for bifurcation analysis, with application to thermo-acoustically unstable systems

Taraneh Sayadi et al.

PHYSICS OF FLUIDS (2015)

Add to Collection

Article Engineering, Mechanical

Bayesian inference applied to spatio-temporal reconstruction of flows around a NACA0012 airfoil

Leroux Romain et al.

EXPERIMENTS IN FLUIDS (2014)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Low cost 3D global instability analysis and flow sensitivity based on dynamic mode decomposition and high-order numerical tools

Esteban Ferrer et al.

INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN FLUIDS (2014)

Add to Collection

Article Engineering, Mechanical

The identification of coherent structures using proper orthogonal decomposition and dynamic mode decomposition

Qingshan Zhang et al.

JOURNAL OF FLUIDS AND STRUCTURES (2014)

Add to Collection

Review Engineering, Aerospace

Reduced order unsteady aerodynamic modeling for stability and control analysis using computational fluid dynamics

Mehdi Ghoreyshi et al.

PROGRESS IN AEROSPACE SCIENCES (2014)

Add to Collection

Article Engineering, Multidisciplinary

Reduced order modelling for unsteady fluid flow using proper orthogonal decomposition and radial basis functions

S. Walton et al.

APPLIED MATHEMATICAL MODELLING (2013)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Reduced-order modeling of transonic flows around an airfoil submitted to small deformations

Remi Bourguet et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2011)

Add to Collection

Article Mechanics

Dynamic mode decomposition of numerical and experimental data

Peter J. Schmid

JOURNAL OF FLUID MECHANICS (2010)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Calibrated reduced-order POD-Galerkin system for fluid flow modelling

M Couplet et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2005)

Add to Collection

Review Engineering, Aerospace

Reduced-order modeling: new approaches for computational physics

DJ Lucia et al.

PROGRESS IN AEROSPACE SCIENCES (2004)

Add to Collection

Article Engineering, Aerospace

Proper orthogonal decomposition technique for transonic unsteady aerodynamic plows

KC Hall et al.

AIAA JOURNAL (2000)

Add to Collection

© Peeref 2019-2024. All rights reserved.