Prediction of Solid Holdup in a Gas–Solid Circulating Fluidized Bed Riser by Artificial Neural Networks

Zhong, Hanbin; Sun, Zeneng; Zhu, Jesse; Zhang, Chao

doi:10.1021/acs.iecr.0c05474

Cited by 22 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yang and co-workers , combined an SVM-based data-driven method and DEM modeling to predict key granular flow parameters such as the angle of repose and collision energy in a rotating drum. Zhong et al proposed an improved strategy beneficial for finding the optimal ANN to significantly enhance predictions of the particle phase fraction distributions in gas-particle CFB risers. This work provides a possibility to reduce experimental workload (up to 1/3 experimental sets) and hence is of practical meaning to experiments, especially for large-scale reactors.…”

Section: Current Status and Challengesmentioning

confidence: 99%

Review of Machine Learning for Hydrodynamics, Transport, and Reactions in Multiphase Flows and Reactors

Zhu

Chen

Ouyang

et al. 2022

Ind. Eng. Chem. Res.

120

View full text Add to dashboard Cite

Artificial intelligence (AI), machine learning (ML), and data science are leading to a promising transformative paradigm. ML, especially deep learning and physics-informed ML, is a valuable toolkit that complements incomplete domain-specific knowledge in conventional experimental and computational methods. ML can provide flexible techniques to facilitate the conceptual development of new robust predictive models for multiphase flows and reactors by finding hidden pattern/information/mechanism in a data set. Due to such emergence, we thereby comprehensively survey, explore, analyze, and discuss key advancements of recent ML applications to hydrodynamics, heat and mass transfer, and reactions in single-phase and multiphase flow systems from different aspects: (1) development of multiphase closure models of drag force, turbulence stresses and heat/mass transfer to improve the accuracy and efficiency of typical CFD simulations; (2) image reconstruction, regime identification, key parameter predictions, and optimization of multiphase flow and transport fields; (3) reaction kinetics modeling (e.g., predictions of reaction networks, kinetic parameters, and species production) and reaction condition optimization. These sections also discuss and analyze the key advantages and weakness of ML for solving the problems in the domain of multiphase flows and reactors. Finally, we summarize the under-solving challenges and opportunities in order to identify future directions that would be useful for the research community. Future development and study of multiphase flows and reactors are envisaged to be accelerated by ML and data science.

show abstract

Section: Current Status and Challengesmentioning

confidence: 99%

Review of Machine Learning for Hydrodynamics, Transport, and Reactions in Multiphase Flows and Reactors

Zhu

Chen

Ouyang

et al. 2022

Ind. Eng. Chem. Res.

120

View full text Add to dashboard Cite

show abstract

“…Its accurate measurement has guiding significance for designing and optimizing the fluidized bed. 6,7 Electrical tomography (ET) mainly uses boundary data to reconstruct the distribution of electrical characteristic parameters of the media in the region of interest (ROI) with the help of a suitable image reconstruction algorithm. It is nonradioactive, nonintrusive, and low-cost and has high-time resolution, which solves many problems of conventional testing technologies.…”

Section: Introductionmentioning

confidence: 99%

“…At present, the specific application fields of magnetic catalysts mainly include solid acid catalysis, solid base catalysis, phase transfer catalysis, photocatalysis and biocatalysis, etc. − To describe the flow state of the gas–liquid–solid three-phase, the three-phase holdup distribution in the cross section of the fluidized bed is one of the key parameters. Its accurate measurement has guiding significance for designing and optimizing the fluidized bed. , …”

Section: Introductionmentioning

confidence: 99%

Measurement of Three-Phase Holdup Distribution in Gas–Liquid–Solid Fluidized Bed Based on ERT/TMR-EMT

Wang,

Zhang,

Guo

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

The measurement of three-phase holdup distributions in the gas−liquid−solid fluidized bed has guiding significance for the fluidized bed's characterization, design, and optimization. Aimed at the measurement of three-phase holdup distribution simultaneously, an image reconstruction method for electrical resistance tomography and electromagnetic tomography based on tunnel magnetoresistance (ERT/TMR-EMT) dual-modality system is proposed. The distributions of equivalent conductivity and equivalent permeability are reconstructed by the D-bar algorithm based on ERT and TMR-EMT, respectively. Then, the three-phase holdup distribution is reconstructed through equivalent media theory. From the results of the reconstructed image and threephase average holdup in simulation, the holdup variations of the gas, liquid, and solid are principally consistent with the phantom sets. From the measurement results of the dynamic experiments, clusters with high solid holdup and bubbles with high gas holdup can be accurately reflected and the variation of three-phase holdup distribution and average holdup can correctly reflect changes in experimental states in the fluidized bed.

show abstract

“…From the literature review, it is noticed that some literature has existed for the application of artificial neural network (ANN) for gas-particle flow in the recent past. [17][18][19] ANN has been used for the ultimate estimation of the drag correction. [20] Recently, ANN has also been coupled with computational fluid dynamics (CFD) modelling, and the conventional prediction method for filter drag, heat transfer, and reaction rate for gas-particle flow.…”

Section: Introductionmentioning

confidence: 99%

Bed expansion of binary mixtures of irregular particles in solid–liquid fluidization: Experimental, empirical correlation, and GA‐ANN modelling

et al. 2022

View full text Add to dashboard Cite

Expansion behaviour for a bed of binary mixture of the irregularly shaped particle in Newtonian liquid was measured in two different circular columns. Variations in the physical parameters on the expansion behaviour have been reported. Bed expansion increases with an increase in liquid velocity and a decrease in particle diameter. Static bed height and expansion of the bed are low for higher diameter columns. An empirical correlation has been developed for predicting the ratio of bed height at the fluidized condition to the initial bed height as a function of the physical and dynamic variables related to the system for the binary particle mixtures. The correlation coefficient and variance of the estimate are 0.9299 and 0.0013, respectively, which is acceptable statistical accuracy. A hybrid of the genetic algorithm and neural network modelling for the prediction of the same has also been attempted where the input parameters are optimized using the Levenberg–Marquardt algorithm. With a relative error of 1.46%, the genetic algorithm performed well. So, the modelling has successfully predicted the bed height ratio at fluidized conditions to the initial bed height.

show abstract

Prediction of Solid Holdup in a Gas–Solid Circulating Fluidized Bed Riser by Artificial Neural Networks

Cited by 22 publications

References 20 publications

Review of Machine Learning for Hydrodynamics, Transport, and Reactions in Multiphase Flows and Reactors

Review of Machine Learning for Hydrodynamics, Transport, and Reactions in Multiphase Flows and Reactors

Measurement of Three-Phase Holdup Distribution in Gas–Liquid–Solid Fluidized Bed Based on ERT/TMR-EMT

Bed expansion of binary mixtures of irregular particles in solid–liquid fluidization: Experimental, empirical correlation, and GA‐ANN modelling

Contact Info

Product

Resources

About