4.6 Article

A hybrid mesoscale closure combining CFD and deep learning for coarse-grid prediction of gas-particle flow dynamics

Related references

Note: Only part of the references are listed.
Article Engineering, Chemical

Development of data-driven filtered drag model for industrial-scale fluidized beds

Yundi Jiang et al.

Summary: The study demonstrated the successful extrapolation of an artificial neural network model to large grid sizes and developed a general model for drag correction that can be applied to various gas and particle characteristics. This is important for understanding the behavior of gas-particle flows on a large scale.

CHEMICAL ENGINEERING SCIENCE (2021)

Article Engineering, Chemical

Coarse-grid simulations of full-loop gas-solid flows using a hybrid drag model: Investigations on turbulence models

Jun-Sen Li et al.

Summary: The study found that the impact of different turbulence models on predictions of fluidization processes in the mesoscale gas-solid flow system varies. By utilizing a hybrid model and different turbulence closure models in a circulating fluidized bed CFB, more accurate predictions of flow characteristics can be achieved.

POWDER TECHNOLOGY (2021)

Article Engineering, Chemical

Analysis and development of homogeneous drag closure for filtered mesoscale modeling of fluidized gas-particle flows

Li-Tao Zhu et al.

Summary: This study investigates the effects of different HDCs on filtered mesoscale model predictions using highly-resolved simulations, showing significant differences between the commonly-practiced Wen-Yu drag closure and DNS-based HDCs in moderate and dense gas-particle flows. At low Reynolds numbers, HDCs from static particle DNS align with dynamic gas-particle flow DNS data, while Wen-Yu drag closure is more suitable for other ranges.

CHEMICAL ENGINEERING SCIENCE (2021)

Article Engineering, Chemical

Machine learning accelerated discrete element modeling of granular flows

Liqiang Lu et al.

Summary: The research accelerated the computation speed of DEM using a convolutional neural network, demonstrating its accuracy and efficiency in the simulation of granular flows through experiments.

CHEMICAL ENGINEERING SCIENCE (2021)

Article Engineering, Chemical

Coupling Artificial Neural Network with EMMS drag for simulation of dense fluidized beds

Zhuo Yang et al.

Summary: In this study, a generic EMMS drag model was developed using Artificial Neural Network (ANN) to simulate dense fluidized beds under a wide range of operating conditions and material properties. The model's algorithm was optimized to efficiently provide a large dataset and the performance of ANN was tested by training with different numbers of data and hidden layer structures. The EMMS-ANN model showed reasonable prediction and good applicability to a wide range of dense fluidization.

CHEMICAL ENGINEERING SCIENCE (2021)

Article Engineering, Chemical

A scale-independent modeling method for filtered drag in fluidized gas-particle flows

Ming Jiang et al.

Summary: A scale-independent modeling method for filtered drag force in fluidized gas-solid flows is proposed, showing excellent performance in a priori and a posteriori tests across different fluidized regimes. Correction methods to consider the material properties were tested but found to be unsuitable for the cases considered.

POWDER TECHNOLOGY (2021)

Article Engineering, Chemical

Data-driven modeling of mesoscale solids stress closures for filtered two-fluid model in gas-particle flows

Bo Ouyang et al.

Summary: This study uses an artificial neural network based machine learning method to perform data-driven modeling of mesoscale solids stress closures in gas-particle flows. The optimization of the loss function shows that coupling two loss functions can lead to more accurate predictions of the solids stresses, and an optimal three-marker mesoscale closure is proposed. Comparative analysis suggests that the data-driven model can substantially enhance prediction accuracy compared to conventional models.

AICHE JOURNAL (2021)

Article Engineering, Chemical

Conventional and data-driven modeling of filtered drag, heat transfer, and reaction rate in gas-particle flows

Li-Tao Zhu et al.

Summary: This study introduces conventional and artificial neural network-based data-driven modeling methods for modeling drag, heat transfer, and reaction rate in gas-particle flows, with a focus on the impact of various parameters. The results show that the predictive accuracy of the data-driven model is higher compared to traditional correlations, and the correction of filtered drag is related to filtered temperature difference markers, while the correction of filtered reaction rate shows weak dependence on additional markers.

AICHE JOURNAL (2021)

Article Engineering, Chemical

CFD simulation of bubble column hydrodynamics with a novel drag model based on EMMS approach

Xiaoping Guan et al.

Summary: The study introduces a new drag model termed DBS-Local derived from the Dual-Bubble-Size (DBS) model based on Energy-Minimization Multi-Scale (EMMS), which improves the prediction of gas holdup and flow characteristics in bubble columns. The DBS-Local model demonstrates the best agreement with experimental results for centerline liquid velocity compared to other drag models.

CHEMICAL ENGINEERING SCIENCE (2021)

Article Engineering, Chemical

Verification and Validation of Spatially Averaged Models for Fluidized Gas-Particle Suspensions

Simon Schneiderbauer

CHEMICAL ENGINEERING & TECHNOLOGY (2020)

Article Engineering, Chemical

Capability assessment of coarse-grid simulation of gas-particle riser flow using sub-grid drag closures

Li-Tao Zhu et al.

CHEMICAL ENGINEERING SCIENCE (2020)

Article Mechanics

A dynamic anisotropic Spatially-Averaged Two-Fluid Model for moderately dense gas-particle flows

Stefanie Rauchenzauner et al.

INTERNATIONAL JOURNAL OF MULTIPHASE FLOW (2020)

Article Engineering, Chemical

Modeling of the filtered drag force in gas-solid flows via a deep learning approach

Yu Zhang et al.

CHEMICAL ENGINEERING SCIENCE (2020)

Article Engineering, Chemical

Do particle-related parameters influence circulating fluidized bed (CFB) riser flux and elutriation?

Jia Wei Chew et al.

CHEMICAL ENGINEERING SCIENCE (2020)

Article Mechanics

Numerical simulation of turbulent gas-solid flow using an approximate deconvolution model

Simon Schneiderbauer et al.

INTERNATIONAL JOURNAL OF MULTIPHASE FLOW (2019)

Article Engineering, Chemical

A material-property-dependent sub-grid drag model for coarse-grained simulation of 3D large-scale CFB risers

Li-Tao Zhu et al.

CHEMICAL ENGINEERING SCIENCE (2019)

Article Engineering, Chemical

Neural-network-based filtered drag model for gas-particle flows

Yundi Jiang et al.

POWDER TECHNOLOGY (2019)

Article Engineering, Chemical

Development and verification of anisotropic solids stress closures for filtered Two Fluid Models

Jan Hendrik Cloete et al.

CHEMICAL ENGINEERING SCIENCE (2018)

Article Engineering, Chemical

Development and verification of anisotropic drag closures for filtered Two Fluid Models

Jan Hendrik Cloete et al.

CHEMICAL ENGINEERING SCIENCE (2018)

Review Engineering, Chemical

Kinetic theory based multiphase flow with experimental verification

Dimitri Gidaspow et al.

REVIEWS IN CHEMICAL ENGINEERING (2018)

Article Engineering, Chemical

An effective three-marker drag model via sub-grid modeling for turbulent fluidization

Li-Tao Zhu et al.

CHEMICAL ENGINEERING SCIENCE (2018)

Article Engineering, Chemical

Filtered sub-grid constitutive models for fluidized gas-particle flows constructed from 3-D simulations

Avik Sarkar et al.

CHEMICAL ENGINEERING SCIENCE (2016)

Article Mechanics

On multiphase turbulence models for collisional fluid-particle flows

Rodney O. Fox

JOURNAL OF FLUID MECHANICS (2014)

Article Engineering, Chemical

Filtered two-fluid models of fluidized gas-particle flows: New constitutive relations

Christian C. Milioli et al.

AICHE JOURNAL (2013)

Article Engineering, Chemical

A functional subgrid drift velocity model for filtered drag prediction in dense fluidized bed

Jean-Francois Parmentier et al.

AICHE JOURNAL (2012)

Article Engineering, Chemical

Fine-grid simulations of gas-solids flow in a circulating fluidized bed

Sofiane Benyahia

AICHE JOURNAL (2012)

Article Engineering, Chemical

Numerical and experimental study on multiple-spout fluidized beds

Maureen S. van Buijtenen et al.

CHEMICAL ENGINEERING SCIENCE (2011)

Article Engineering, Chemical

Constitutive Models for Filtered Two-Fluid Models of Fluidized Gas-Particle Flows

Yesim Igci et al.

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH (2011)

Article Multidisciplinary Sciences

Detecting Novel Associations in Large Data Sets

David N. Reshef et al.

SCIENCE (2011)

Article Computer Science, Artificial Intelligence

Unsupervised Learning of Probabilistic Grammar-Markov Models for Object Categories

Long (Leo) Zhu et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2009)

Review Engineering, Chemical

A Review of Eulerian Simulation of Geldart A Particles in Gas-Fluidized Beds

Junwu Wang

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH (2009)

Article Engineering, Chemical

Filtered two-fluid models for fluidized gas-particle suspensions

Yesim Igci et al.

AICHE JOURNAL (2008)

Article Engineering, Chemical

Detailed measurements of flow structure inside a dense gas-solids fluidized bed

Haiyan Zhu et al.

POWDER TECHNOLOGY (2008)

Article Computer Science, Artificial Intelligence

A fast learning algorithm for deep belief nets

Geoffrey E. Hinton et al.

NEURAL COMPUTATION (2006)

Article Mechanics

The role of meso-scale structures in rapid gas-solid flows

K Agrawal et al.

JOURNAL OF FLUID MECHANICS (2001)

Article Computer Science, Artificial Intelligence

Efficient deformable template detection and localization without user initialization

J Coughlan et al.

COMPUTER VISION AND IMAGE UNDERSTANDING (2000)