Artificial neural network model for predicting minimum fluidization velocity and maximum pressure drop of gas fluidized bed with different particle size distributions

Abstract The minimum fluidization velocity (Umf) and maximum pressure drop (ΔPmax)of a gas-solid fluidized bed are important hydrodynamic characteristics. The accurate information of these characteristics is required for obtaining the optimum design and operating conditions. In this study, a multi-layer perceptron (MLP) based on an artificial neural network was developed to accurately predict these hydrodynamic characteristics dealing with the influence of the particle size distribution (PSD). The MLP model parameters were adjusted by the backpropagation learning algorithm using wide ranges of experimental data from conducted experiments and collected literature. The five influential dimensionless groups of parameters were used for simultaneous estimation of the Umf and ΔPmax. Statistical accuracy analysis confirmed that a two-layer feedforward with thirteen hidden neurons was the best architecture for the MLP model in terms of absolute average relative deviation (AARD), mean square error (MSE) and regression coefficient (R2). The accuracy of Umf and ΔPmax was 10.36 % and 8.35 % with AARD, 1.7 × 10−4 and 0.0188 with MSE, and 0.9935 and 0.9152 by R2, respectively. Besides, the predictive performance of the developed model was compared with other literature models. The comparison shows the performance of the developed MLP model was acceptable.

[1]  R. R. Pattipati,et al.  Minimum fluidization velocity at high temperatures , 1981 .

[2]  N. Anantharaman,et al.  Hydrodynamic studies in fluidized bed with internals and modeling using ANN and ANFIS , 2017 .

[3]  R. Xiao,et al.  Fluidization of Biomass Particles in a Gas−Solid Fluidized Bed , 2008 .

[4]  Derek Geldart,et al.  The effect of particle size and size distribution on the behaviour of gas-fluidised beds , 1972 .

[5]  J. G. Yates,et al.  Fluidization engineering: Second edition , 1993 .

[6]  I. Topcu,et al.  Prediction of mechanical properties of recycled aggregate concretes containing silica fume using artificial neural networks and fuzzy logic , 2008 .

[7]  G. Karimi,et al.  Prediction of thermal conductivity of alumina water-based nanofluids by artificial neural networks , 2015 .

[8]  Joachim Denzler,et al.  Deep learning and process understanding for data-driven Earth system science , 2019, Nature.

[9]  C. Onu,et al.  Evaluation of optimization techniques in predicting optimum moisture content reduction in drying potato slices , 2020 .

[10]  Effect of Particle Size Distributions on Minimum Fluidization Velocity with Varying Gas Temperature , 2020 .

[11]  D. Mowla,et al.  Modeling and analysis of effective thermal conductivity of sandstone at high pressure and temperature using optimal artificial neural networks , 2014 .

[12]  Pornpote Piumsomboon,et al.  Revised fluidization regime characterization in high solid particle concentration circulating fluidized bed reactor , 2014 .

[13]  Hai-bin Qu,et al.  Modeling of the Minimum Fluidization Velocity and the Incipient Fluidization Pressure Drop in a Conical Fluidized Bed with Negative Pressure , 2020, Applied Sciences.

[14]  Hariprasad J. Subramani,et al.  Minimum fluidization velocity at elevated temperatures for Geldart’s group-B powders , 2007 .

[15]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[16]  Temel Varol,et al.  Analysis of the effect of a new process control agent technique on the mechanical milling process using a neural network model: Measurement and modeling , 2013 .

[17]  C. Xiaoping,et al.  Minimum fluidization velocity of particles with wide size distribution at high temperatures , 2013 .

[18]  Yurong He,et al.  Drag coefficient prediction for non-spherical particles in dense gas–solid two-phase flow using artificial neural network , 2019, Powder Technology.

[19]  Dražen Lončar,et al.  Artificial neural network modelling approach for a biomass gasification process in fixed bed gasifiers. , 2014 .

[20]  Arnaud Delebarre,et al.  Influence of the bed mass on its fluidization characteristics , 2004 .

[21]  Xiaoping Chen,et al.  Hydrodynamic characteristics of spout-fluid bed: Pressure drop and minimum spouting/spout-fluidizing velocity , 2006 .

[22]  D. Gauthier,et al.  Influence of the particle size distribution of powders on the velocities of minimum and complete fluidization , 1999 .

[23]  Behzad Vaferi,et al.  Artificial neural network approach for prediction of thermal behavior of nanofluids flowing through circular tubes , 2014 .

[24]  Jan Baeyens,et al.  Effect of operating temperature on minimum fluidization velocity , 1991 .

[25]  D. Geldart.  Types of gas fluidization , 1973 .

[26]  Seyyed Hossein Hosseini,et al.  Smart computing approach for design and scale-up of conical spouted beds with open-sided draft tubes , 2021, Particuology.

[27]  Han-Chung Yang,et al.  Potential hazard analysis from the viewpoint of flow measurement in large open-channel junctions , 2012, Natural Hazards.

[28]  J. Grace,et al.  Hydrodynamics of gas-solid fluidization , 1995 .

[29]  Martin T. Hagan,et al.  Neural network design , 1995 .

[30]  C. Onu,et al.  Comparative analysis of RSM, ANN and ANFIS and the mechanistic modeling in eriochrome black-T dye adsorption using modified clay , 2021, South African Journal of Chemical Engineering.

[31]  C. Wen,et al.  A generalized method for predicting the minimum fluidization velocity , 1966 .

[32]  M. Azizi,et al.  Comparison between the artificial neural network, SAFT and PRSV approach in obtaining the solubility of solid aromatic compounds in supercritical carbon dioxide , 2013 .

[33]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[34]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[35]  B. Chalermsinsuwan,et al.  Effect of operating parameters inside circulating fluidized bed reactor riser with ring baffles using CFD simulation and experimental design analysis , 2014 .

[36]  W. Khan,et al.  Effect of Initial Static Bed Height and Liquid Superficial Velocity on the Minimum Fluidization Velocity (Umf) and Pressure Drop for the Bed of Semolina Particles in Liquid-Solid Fluidization , 2016 .

[37]  A. Yu,et al.  Minimum fluidization velocity of particles with different size distributions at elevated pressures and temperatures , 2020 .

[38]  M. H. Khani.  Models for prediction of hydrodynamic characteristics of gas–solid tapered and mini-tapered fluidized beds , 2011 .

[39]  S. Das,et al.  Non-spherical solid-non-Newtonian liquid fluidization and ANN modelling: Minimum fluidization velocity , 2018 .

[40]  C. Duan,et al.  Minimum fluidization velocity growth due to bed inventory increase in an Air Dense Medium Fluidized Bed , 2019, Chemical Engineering Journal.

[41]  Musademba Downmore,et al.  Effect of bed particle size and temperature variation on the minimum fluidisation velocity: A comparison with minimum fluidisation velocity correlations for bubbling fluidised bed designs , 2019, Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering.

[42]  Temel Varol,et al.  Artificial neural network modeling to effect of reinforcement properties on the physical and mechanical properties of Al2024–B4C composites produced by powder metallurgy , 2013 .

[43]  Jörg Imberger,et al.  Environmental Fluid Dynamics: Flow Processes, Scaling, Equations of Motion, and Solutions to Environmental Flows , 2012 .

[44]  J. T. Freire,et al.  Fitting performance of artificial neural networks and empirical correlations to estimate higher heating values of biomass , 2016 .

[45]  F. Farhadi,et al.  Hydrodynamic characteristics of gas–solid tapered fluidized beds: Experimental studies and empirical models , 2015 .

[46]  D. Gidaspow,et al.  In-depth system parameters of transition flow pattern between turbulent and fast fluidization regimes in high solid particle density circulating fluidized bed reactor , 2014 .

[47]  Qing Sun,et al.  Recent developments of artificial intelligence in drying of fresh food: A review , 2019, Critical reviews in food science and nutrition.

[48]  Ehsan Kamrani,et al.  A Neural Network Model for Determining the Success or Failure of High-tech Projects Development: A Case of Pharmaceutical industry , 2018, ArXiv.

[49]  L. Fan,et al.  Hydrodynamic characteristics of fluidization in liquid-solid tapered beds , 1997 .

[50]  Chuanlong Xu,et al.  Flow characteristics in pressurized oxy-fuel fluidized bed under hot condition , 2018, International Journal of Multiphase Flow.

[51]  Jamil Shafi,et al.  ANN and RSM based modelling for optimization of cell dry mass of Bacillus sp. strain B67 and its antifungal activity against Botrytis cinerea , 2018 .

[52]  Behzad Vaferi,et al.  Automatic recognition of oil reservoir models from well testing data by using multi-layer perceptron networks , 2011 .

[53]  S. Ergun.  Fluid flow through packed columns , 1952 .

[54]  Behzad Vaferi,et al.  Phase equilibria modeling of binary systems containing ethanol using optimal feedforward neural network , 2013 .

[55]  K. Biswal,et al.  Minimum fluidization velocities and maximum bed pressure drops for gas-solid tapered fluidized beds , 2007 .

[56]  Junfu Lu,et al.  Characterization of gas–solid fluidization in fluidized beds with different particle size distributions by analyzing pressure fluctuations in wind caps , 2018, Chemical Engineering Journal.

[57]  M. Wey,et al.  The effect of particle size distribution on minimum fluidization velocity at high temperature , 2002 .

[58]  Jia Wei Chew,et al.  Application of machine learning methods to understand and predict circulating fluidized bed riser flow characteristics , 2020 .

[59]  G. Ahmadi,et al.  Empirical models for minimum fluidization velocity of particles with different size distribution in tapered fluidized beds , 2018, Powder Technology.