Integration of first-principle models and machine learning in a modeling framework: An application to flocculation

Abstract In this paper, an integrated hybrid modeling approach with first-principles is implemented to model a flocculation process. The application of the framework is demonstrated through a laboratory-scale flocculation case of silica particles in water. In this modeling framework, it is demonstrated that the integration of first-principles models and machine-learning approaches accurately predicts the dynamics of the system. The first-principles model used in this study incorporates a population balance and mass balance models combined with the kinetic expressions of the agglomeration and breakage phenomena. The prediction of such modeling framework is compared with a fully first-principles model, and moreover with a hybrid model that was developed in a prior work, which used a population balance model as the first principles model and a deep learning algorithm for the determination of the flocculation kinetic parameters.

[1]  Z. Gu,et al.  Advances in numerical methods for the solution of population balance equations for disperse phase systems , 2009 .

[2]  Krist V Gernaey,et al.  Towards smart biomanufacturing: a perspective on recent developments in industrial measurement and monitoring technologies for bio-based production processes , 2020, Journal of industrial microbiology & biotechnology.

[3]  Lyle H. Ungar,et al.  A hybrid neural network‐first principles approach to process modeling , 1992 .

[4]  Krist V. Gernaey,et al.  Novel strategies for predictive particle monitoring and control using advanced image analysis , 2019, Computer Aided Chemical Engineering.

[5]  Rui Oliveira.  Combining first principles modelling and artificial neural networks: a general framework , 2004, Comput. Chem. Eng..

[6]  Darsh T. Wasan,et al.  Emulsion stability — kinetics of flocculation and coalescence , 1992 .

[7]  Patrick T. Spicer,et al.  Laminar and turbulent shear-induced flocculation of fractal aggregates , 1999 .

[8]  Prodromos Daoutidis,et al.  Numerical solution of multi-variable cell population balance models. III. Finite element methods , 2001 .

[9]  X. Qian,et al.  Flocculation of biological cells: Experiment vs. theory , 2003 .

[10]  S. Dobberschütz,et al.  First-principles prediction of surface wetting. , 2020, Langmuir : the ACS journal of surfaces and colloids.

[11]  Krist V. Gernaey,et al.  Hybrid machine learning assisted modelling framework for particle processes , 2020, Comput. Chem. Eng..

[12]  R. Yoon,et al.  Application of Extended DLVO Theory: II. Stability of Silica Suspensions , 1993 .

[13]  John Gregory,et al.  Monitoring particle aggregation processes. , 2009, Advances in colloid and interface science.

[14]  Phillip D. Fawell,et al.  Population balance modelling to describe the particle aggregation process: A review , 2018 .

[15]  Daniele Marchisio,et al.  Solution of population balance equations using the direct quadrature method of moments , 2005 .

[16]  Michael J. Hounslow,et al.  Finite-element methods for steady-state population balance equations , 1998 .

[17]  Simon Judd,et al.  Flocculation modelling : A review , 1999 .

[18]  C. Negro,et al.  Flocculation mechanism induced by phenolic resin/PEO and floc properties , 2005 .

[19]  P. Somasundaran,et al.  Modeling flocculation of colloidal mineral suspensions using population balances , 2003 .

[20]  M. Tempel.  Stability of oil-in-water emulsions II: Mechanism of the coagulation of an emulsion , 2010 .

[21]  M. Mellema,et al.  Relating colloidal particle interactions to gel structure using Brownian dynamics simulations and the Fuchs stability ratio , 1999 .

[22]  Subhash Bhatia,et al.  Population Balance Model (PBM) for flocculation process: Simulation and experimental studies of palm oil mill effluent (POME) pretreatment , 2008 .

[23]  Alan W. Mahoney,et al.  Population balance modeling. Promise for the future , 2002 .

[24]  Michael F. Malone,et al.  Experimental studies and population balance equation models for breakage prediction of emulsion drop size distributions , 2009 .

[25]  Krist V. Gernaey,et al.  A Hybrid Model Predictive Control Strategy using Neural Network Based Soft Sensors for Particle Processes , 2020 .

[26]  Chi Wai Hui,et al.  A Revision of Population Balance Equation Applied to Microalgae with Birth, Growth, and Death , 2018, Process Integration and Optimization for Sustainability.