☆ 4.5 Article

Interpretable machine learning analysis and automated modeling to simulate fluid-particle flows

PARTICUOLOGY (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Interdisciplinary Applications

Physics-inspired architecture for neural network modeling of forces and torques in particle-laden flows

Arman Seyed-Ahmadi et al.

Summary: We propose a physics-inspired neural network model for direct prediction of forces and torques on particles in random arrays of spheres. By reducing the number of free parameters, the model is able to control complexity without sacrificing accuracy. The study demonstrates the feasibility of using neural networks for direct force and torque prediction only when the model structure corresponds to the underlying physics of the problem.

COMPUTERS & FLUIDS (2022)

Add to Collection

Article Engineering, Chemical

A Machine Learning Study of Predicting Mixing and Segregation Behaviors in a Bidisperse Solid-Liquid Fluidized Bed

Zhouzun Xie et al.

Summary: In this study, a CNN-LSTM model is used to predict the mixing and segregation behaviors in a bidisperse solid-liquid fluidized bed. The CNN-LSTM model shows better training effects than the LSTM model and can provide reliable predictions and characterization of the behaviors. Additionally, the CNN-LSTM model has high efficiency and accuracy in terms of computation time cost.

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH (2022)

Add to Collection

Article Engineering, Chemical

Deep learning methods for predicting fluid forces in dense particle suspensions

Neil Raj Ashwin et al.

Summary: Two deep learning methods, MLP network and CNN, were evaluated for predicting drag forces in dense suspensions of ellipsoidal particles. The CNN outperformed the MLP in most testing levels, except when testing on an unseen aspect ratio.

POWDER TECHNOLOGY (2022)

Add to Collection

Article Health Care Sciences & Services

Explainable Artificial Intelligence for Prediction of Complete Surgical Cytoreduction in Advanced-Stage Epithelial Ovarian Cancer

Alexandros Laios et al.

Summary: This study developed an AI-based predictive model for the outcome of R0 resection in patients with epithelial ovarian cancer. The model showed high accuracy and provided feature explainability. Factors that increased the probability of complete cytoreduction were identified, which can be used for quality control and internal audit purposes.

JOURNAL OF PERSONALIZED MEDICINE (2022)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Interpretable machine learning models for crime prediction

Xu Zhang et al.

Summary: The interpretability of advanced machine learning models is utilized in this study to overcome the limitation of estimating variable contributions in crime prediction. Based on routine activity theory and crime pattern theory, 17 variables are selected for crime prediction, and the Shapley additive explanation (SHAP) method is used to discern the contribution of individual variables. Findings reveal that the proportion of the non-local population and the ambient population aged 25-44 contribute the most to crime prediction. Local models provide insights for tackling important factors at each location, while the global model identifies essential factors for the entire region.

COMPUTERS ENVIRONMENT AND URBAN SYSTEMS (2022)

Add to Collection

Article Energy & Fuels

A subsurface machine learning approach at hydrocarbon production recovery & resource estimates for unconventional reservoir systems: Making subsurface predictions from multimensional data analysis

Shane J. Prochnow et al.

Summary: An innovative, practical, and successful subsurface machine learning workflow is introduced, named ALICE, which has changed the way Chevron manages its tight rock and unconventional assets by utilizing structured reservoir, geologic, engineering and production data.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2022)

Add to Collection

Article Engineering, Chemical

A data-driven approach for the quick prediction of in-furnace phenomena of pulverized coal combustion in an ironmaking blast furnace

Yiran Liu et al.

CHEMICAL ENGINEERING SCIENCE (2022)

Add to Collection

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)

Add to Collection

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)

Add to Collection

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)

Add to Collection

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)

Add to Collection

Article Multidisciplinary Sciences

An improved algorithm for the maximal information coefficient and its application

Dan Cao et al.

Summary: The paper introduces the BackMIC algorithm for MIC estimation, which improves grid partition and MIC values compared to the original algorithm. It shows better clustering results for cancer datasets and more credible correlations between samples than other algorithms.

ROYAL SOCIETY OPEN SCIENCE (2021)

Add to Collection

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)

Add to Collection

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)

Add to Collection

Article Physics, Fluids & Plasmas

Neural Network-Based Model Reduction of Hydrodynamics Forces on an Airfoil

Hamayun Farooq et al.

Summary: An artificial neural network-based reduced order model was developed to predict hydrodynamics forces on an airfoil at different angles of attack using proper orthogonal decomposition. The model was trained using pressure coefficients and successfully validated on both in-sample and out-of-sample data, demonstrating good agreement with true numerical data.

FLUIDS (2021)

Add to Collection

Article Engineering, Chemical

Scale and structure dependent drag in gas-solid flows

Xiaowen Liu et al.

AICHE JOURNAL (2020)

Add to Collection

Article Engineering, Chemical

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

Simon Schneiderbauer

CHEMICAL ENGINEERING & TECHNOLOGY (2020)

Add to Collection

Review Computer Science, Hardware & Architecture

Techniques for Interpretable Machine Learning

Mengnan Du et al.

COMMUNICATIONS OF THE ACM (2020)

Add to Collection

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)

Add to Collection

Article Engineering, Chemical

Machine learning to assist filtered two-fluid model development for dense gas-particle flows

Li-Tao Zhu et al.

AICHE JOURNAL (2020)

Add to Collection

Article Engineering, Chemical

Application of machine learning methods to understand and predict circulating fluidized bed riser flow characteristics

Jia Wei Chew et al.

CHEMICAL ENGINEERING SCIENCE (2020)

Add to Collection

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)

Add to Collection

Article Energy & Fuels

Effect of turbulence modeling on hydrodynamics of a turbulent contact absorber

Atta Ullah et al.

CHEMICAL ENGINEERING AND PROCESSING-PROCESS INTENSIFICATION (2020)

Add to Collection

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)

Add to Collection

Article Ergonomics

Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis

Amir Bahador Parsa et al.

ACCIDENT ANALYSIS AND PREVENTION (2020)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Machine learning for fast and reliable solution of time-dependent differential equations

F. Regazzoni et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2019)

Add to Collection

Article Engineering, Chemical

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

Yundi Jiang et al.

POWDER TECHNOLOGY (2019)

Add to Collection

Article Engineering, Chemical

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

Jan Hendrik Cloete et al.

CHEMICAL ENGINEERING SCIENCE (2018)

Add to Collection

Review Engineering, Chemical

Kinetic theory based multiphase flow with experimental verification

Dimitri Gidaspow et al.

REVIEWS IN CHEMICAL ENGINEERING (2018)

Add to Collection

Review Chemistry, Applied

Toward Constitutive Models for Momentum, Species, and Energy Transport in Gas-Particle Flows

Sankaran Sundaresan et al.

ANNUAL REVIEW OF CHEMICAL AND BIOMOLECULAR ENGINEERING, VOL 9 (2018)

Add to Collection

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)

Add to Collection

Article Engineering, Chemical

A comparative assessment of empirical and lattice Boltzmann method-based drag models for simulation of gas-solid flow hydrodynamics in a bubbling fluidized bed

Carlos M. Romero Luna et al.

PARTICUOLOGY (2017)

Add to Collection

Article Mechanics

Towards filtered drag force model for non-cohesive and cohesive particle-gas flows

Ali Ozel et al.

PHYSICS OF FLUIDS (2017)

Add to Collection

Article Engineering, Chemical

A Spatially-Averaged Two-Fluid Model for Dense Large-Scale Gas-Solid Flows

Simon Schneiderbauer

AICHE JOURNAL (2017)

Add to Collection

Article Engineering, Chemical

Direct Numerical Simulations of Dynamic Gas-Solid Suspensions

Yali Tang et al.

AICHE JOURNAL (2016)

Add to Collection

Article Engineering, Chemical

Filtered model for the cold-model gas-solid flow in a large-scale MTO fluidized bed reactor

Li-Tao Zhu et al.

CHEMICAL ENGINEERING SCIENCE (2016)

Add to Collection

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)

Add to Collection

Article Mechanics

On fluid-particle dynamics in fully developed cluster-induced turbulence

Jesse Capecelatro et al.

JOURNAL OF FLUID MECHANICS (2015)

Add to Collection

Article Engineering, Chemical

Filtered and Heterogeneity-Based Subgrid Modifications for Gas-Solid Drag and Solid Stresses in Bubbling Fluidized Beds

Simon Schneiderbauer et al.

AICHE JOURNAL (2014)

Add to Collection

Article Engineering, Chemical

EMMS-based discrete particle method (EMMS-DPM) for simulation of gas-solid flows

Liqiang Lu et al.

CHEMICAL ENGINEERING SCIENCE (2014)

Add to Collection

Article Engineering, Chemical

A drag model for filtered Euler-Lagrange simulations of clustered gas-particle suspensions

Stefan Radl et al.

CHEMICAL ENGINEERING SCIENCE (2014)

Add to Collection

Article Engineering, Chemical

Comparative Analysis of Subgrid Drag Modifications for Dense Gas-Particle Flows in Bubbling Fluidized Beds

Simon Schneiderbauer et al.

AICHE JOURNAL (2013)

Add to Collection

Article Engineering, Chemical

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

Christian C. Milioli et al.

AICHE JOURNAL (2013)

Add to Collection

Article Engineering, Chemical

Lattice Boltzmann based discrete simulation for gas-solid fluidization

Limin Wang et al.

CHEMICAL ENGINEERING SCIENCE (2013)

Add to Collection

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)

Add to Collection

Article Engineering, Chemical

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

Yesim Igci et al.

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH (2011)

Add to Collection

Article Mechanics

Drag law for monodisperse gas-solid systems using particle-resolved direct numerical simulation of flow past fixed assemblies of spheres

S. Tenneti et al.

INTERNATIONAL JOURNAL OF MULTIPHASE FLOW (2011)

Add to Collection

Editorial Material Multidisciplinary Sciences

A Correlation for the 21st Century

Terry Speed

SCIENCE (2011)

Add to Collection

Article Multidisciplinary Sciences

Detecting Novel Associations in Large Data Sets

David N. Reshef et al.

SCIENCE (2011)

Add to Collection

Article Engineering, Chemical

Filtered two-fluid models for fluidized gas-particle suspensions

Yesim Igci et al.

AICHE JOURNAL (2008)

Add to Collection

Article Engineering, Chemical

Drag force of intermediate Reynolds number flow past mono- and bidisperse arrays of spheres

R. Beetstra et al.

AICHE JOURNAL (2007)

Add to Collection

Article Mechanics

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

K Agrawal et al.

JOURNAL OF FLUID MECHANICS (2001)

Add to Collection

© Peeref 2019-2024. All rights reserved.