Machine-Learning models for the prediction of the drag force exerted by a shear-thinning viscoelastic fluid in a sphere

Apresentação efetuada no 9th OpenFOAM Conference, em Worldwide, ONLINE, 2021[Excerpt] Non-Newtonian fluid suspensions are widely used in several areas of our daily life, e.g., to produce bags, toys, car components, textiles, etc., and they are also commonly encountered in many advanced manufacturing and industrial operations, such as processing of battery slurries or hydraulic fracturing operations. However, an efficient numerical solver capable of simulating such processes is still missing in the scientific literature. For this purpose, a 3D CFD-DEM viscoelastic solver is developed in this work to handle particle-laden viscoelastic flows using a new approach, based on machine learning and deep learning models [1-3], to compute a particulate-phase drag model valid for a wide range of material parameters.This work is funded by FEDER funds through the COMPETE 2020 Programme and National Funds through FCT (Portuguese Foundation for Science and Technology) under the projects UID-B/05256/2020, UID-P/05256/2020, APROVA-Aprendizagem PROfunda na modelação de escoamentos com fluidos de matriz Viscoelástica Aditivados com partículas (POCI-01-0145- FEDER-016665) and HPC-EUROPA3 (INFRAIA-2016-1-730897). The authors would like to acknowledge the Minho University cluster under the project NORTE-07-0162- FEDER-000086 (URL: http://search6.di.uminho.pt), the Minho Advanced Computing Center (MACC) (URL: https://macc.fccn.pt), the Texas Advanced Computing Center (TACC) at The University of Texas at Austin (URL: http://www.tacc.utexas.edu), the Gompute HPC Cloud Platform (URL: https://www.gompute.com) and Consorzio Interuniversitario dell’Italia Nord Est per il Calcolo Automatico (CINECA) for providing HPC resources that have contributed to the research results reported within this paper