Introducing an artificial neural network energy minimization multi-scale drag scheme for fluidized particles

Abstract Particles under fluidization conditions tend to clog and aggregate, and form meso–scale structures that significantly affect gas-solid transport phenomena. In the last decade, resolution of multi–scale particle structures has been attained by using advanced sub-grid models, such as the Energy Minimization Multi-Scale (EMMS) scheme. The current work aims to develop an ANN (Artificial Neural Network) to better resolve the effect of such structures. The ANN is developed, trained and validated using data generated by a custom-built FORTRAN code that solves the EMMS equations for a wide variety of gas-particle mixture properties (1

[1]  Alexander Daikeler,et al.  Coarse grain 3D CFD-DEM simulation and validation with capacitance probe measurements in a circulating fluidized bed , 2019, Chemical Engineering Science.

[2]  Wei Wang,et al.  Searching for a mesh-independent sub-grid model for CFD simulation of gas–solid riser flows , 2009 .

[3]  Daizo Kunii,et al.  CHAPTER 3 – Fluidization and Mapping of Regimes , 1991 .

[4]  Xizhong Chen,et al.  Mesoscale-structure-based dynamic multiscale method for gas-solid flow , 2018, Chemical Engineering Science.

[5]  Rajkumar Thirumalainambi,et al.  Training data requirement for a neural network to predict aerodynamic coefficients , 2003, SPIE Defense + Commercial Sensing.

[6]  Xinhua Liu,et al.  A general EMMS drag model applicable for gas-solid turbulent beds and cocurrent downers , 2019, Chemical Engineering Science.

[7]  Fabio Montagnaro,et al.  Directly irradiated fluidized bed reactors for thermochemical processing and energy storage: Application to calcium looping , 2017 .

[8]  D. Subbarao,et al.  A model for cluster size in risers , 2010 .

[9]  D. R. Baughman,et al.  Fundamental and Practical Aspects of Neural Computing , 1995 .

[10]  Jari Kolehmainen,et al.  Neural-network-based filtered drag model for gas-particle flows , 2019, Powder Technology.

[11]  Wei Wang,et al.  Simulation of gas-solid two-phase flow by a multi-scale CFD approach - Extension of the EMMS model to the sub-grid level , 2007 .

[12]  Panagiotis Grammelis,et al.  High-resolution 3-D full-loop simulation of a CFB carbonator cold model , 2013 .

[13]  R. Jackson,et al.  Frictional–collisional constitutive relations for granular materials, with application to plane shearing , 1987, Journal of Fluid Mechanics.

[14]  Olivier Simonin,et al.  Development of filtered Euler–Euler two-phase model for circulating fluidised bed: High resolution simulation, formulation and a priori analyses , 2013 .

[15]  Soteris A. Kalogirou,et al.  Applications of artificial neural-networks for energy systems , 2000 .

[16]  Danesh K. Tafti,et al.  A supervised machine learning approach for predicting variable drag forces on spherical particles in suspension , 2019, Powder Technology.

[17]  Liqiang Lu,et al.  Development and validation of an enhanced filtered drag model for simulating gas-solid fluidization of Geldart A particles in all flow regimes , 2018, Chemical Engineering Science.

[18]  Panagiotis Grammelis,et al.  An advanced EMMS scheme for the prediction of drag coefficient under a 1.2 MWth CFBC isothermal flow—Part II: Numerical implementation , 2010 .

[19]  Jochen Ströhle,et al.  Carbonate looping experiments in a 1 MWth pilot plant and model validation , 2014 .

[20]  Wei Wang,et al.  A steady-state EMMS drag model for fluidized beds , 2020, Chemical Engineering Science.

[21]  Jinghai Li,et al.  A multiscale mass transfer model for gas-solid riser flows: Part 1 - Sub-grid model and simple tests , 2008 .

[22]  Quan Zhou,et al.  CFD study of mixing and segregation in CFB risers: Extension of EMMS drag model to binary gas–solid flow , 2015 .

[23]  Nikos E. Mastorakis,et al.  Computational Problems in Science and Engineering , 2015 .

[24]  Quan Zhou,et al.  An EMMS drag model for coarse grid simulation of polydisperse gas–solid flow in circulating fluidized bed risers , 2019, Chemical Engineering Science.

[25]  Arthur T. Andrews,et al.  Filtered two‐fluid models for fluidized gas‐particle suspensions , 2008 .

[26]  R. L. Hardy.  Theory and applications of the multiquadric-biharmonic method : 20 years of discovery 1968-1988 , 1990 .

[27]  Hadrien Benoit,et al.  On-sun demonstration of a 750 °C heat transfer fluid for concentrating solar systems: Dense particle suspension in tube , 2015 .

[28]  Hadrien Benoit,et al.  Dense suspension of solid particles as a new heat transfer fluid for concentrated solar thermal plants: on-sun proof of concept , 2013 .

[29]  Jinghai Li,et al.  Virtual experimentation through 3D full-loop simulation of a circulating fluidized bed , 2008 .

[30]  Li-Tao Zhu,et al.  Machine learning to assist filtered two‐fluid model development for dense gas–particle flows , 2020 .

[31]  Anders Lyngfelt,et al.  11,000 h of chemical-looping combustion operation—Where are we and where do we want to go? , 2019, International Journal of Greenhouse Gas Control.

[32]  Alberto Gómez-Barea,et al.  Measurement and theoretical prediction of char temperature oscillation during fluidized bed combustion , 2018, Combustion and Flame.

[33]  S. C. Kaushik,et al.  Assessment of diffuse solar energy under general sky condition using artificial neural network , 2009 .

[34]  C. Wen.  Mechanics of Fluidization , 1966 .

[35]  Hamid Arastoopour,et al.  CFD Simulation of CO2 Sorption in a Circulating Fluidized Bed Using Deactivation Kinetic Model , 2011 .

[36]  Joachim Werther,et al.  CFD-simulation of a circulating fluidized bed riser , 2009 .

[37]  Panagiotis Grammelis,et al.  Simulation of the reacting flow within a pilot scale calciner by means of a three phase TFM model , 2017 .

[38]  G. Flamant.  Theoretical and experimental study of radiant heat transfer in a solar fluidized‐bed receiver , 1982 .

[39]  C. M. Roach,et al.  Fast curve fitting using neural networks , 1992 .

[40]  Daizo Kunii.  Chemical Reaction Engineering and Research and development of gas solid systems , 1980 .

[41]  Wei Wang,et al.  MP-PIC simulation of CFB riser with EMMS-based drag model , 2012 .

[42]  Jesse Zhu,et al.  A Comprehensive Characterization of Aggregative Flow in a Circulating Fluidized Bed (2): High-Density Downer , 2020 .

[43]  Sofiane Benyahia,et al.  Verification and validation study of some polydisperse kinetic theories , 2008 .

[44]  S. Subramaniam,et al.  Development of a gas–solid drag law for clustered particles using particle-resolved direct numerical simulation , 2016 .

[45]  Thomas J. Flynn,et al.  Fluidized-bed technology enabling the integration of high temperature solar receiver CSP systems with steam and advanced power cycles , 2015 .

[46]  C.M.H. Brereton,et al.  Modelling of circulating fluidised-bed solids flow and distribution , 1992 .

[47]  A. Sánchez-Biezma,et al.  Demonstration of steady state CO2 capture in a 1.7 MWth Calcium looping pilot , 2013 .

[48]  Panagiotis Grammelis,et al.  Application of an advanced coupled EMMS-TFM model to a pilot scale CFB carbonator , 2015 .

[49]  Xin Sun,et al.  Filtered sub-grid constitutive models for fluidized gas-particle flows constructed from 3-D simulations , 2016 .

[50]  A. V. Olgac,et al.  Performance Analysis of Various Activation Functions in Generalized MLP Architectures of Neural Networks , 2011 .

[51]  Leon R. Glicksman,et al.  Simplified scaling relationships for fluidized beds , 1993 .

[52]  Wei Ge,et al.  Eulerian simulation of heterogeneous gas–solid flows in CFB risers: EMMS-based sub-grid scale model with a revised cluster description , 2008 .

[53]  Wei Ge,et al.  Effect of particle clusters on mass transfer between gas and particles in gas-solid flows , 2017 .

[54]  Jing Lei,et al.  3D full-loop simulation and experimental verification of gas-solid flow hydrodynamics. in a dense circulating fluidized bed , 2014 .