TY - JOUR
T1 - Physics-Guided Deep Learning for Drag Force Prediction in Dense Fluid-Particulate Systems
AU - Muralidhar, Nikhil
AU - Bu, Jie
AU - Cao, Ze
AU - He, Long
AU - Ramakrishnan, Naren
AU - Tafti, Danesh
AU - Karpatne, Anuj
N1 - Publisher Copyright:
© Copyright 2020, Mary Ann Liebert, Inc.
PY - 2020/10/1
Y1 - 2020/10/1
N2 - Physics-based simulations are often used to model and understand complex physical systems in domains such as fluid dynamics. Such simulations, although used frequently, often suffer from inaccurate or incomplete representations either due to their high computational costs or due to lack of complete physical knowledge of the system. In such situations, it is useful to employ machine learning (ML) to fill the gap by learning a model of the complex physical process directly from simulation data. However, as data generation through simulations is costly, we need to develop models being cognizant of data paucity issues. In such scenarios, it is helpful if the rich physical knowledge of the application domain is incorporated in the architectural design of ML models. We can also use information from physics-based simulations to guide the learning process using aggregate supervision to favorably constrain the learning process. In this article, we propose PhyNet, a deep learning model using physics-guided structural priors and physics-guided aggregate supervision for modeling the drag forces acting on each particle in a computational fluid dynamics-discrete element method. We conduct extensive experiments in the context of drag force prediction and showcase the usefulness of including physics knowledge in our deep learning formulation. PhyNet has been compared with several state-of-the-art models and achieves a significant performance improvement of 7.09% on average. The source code has been made available∗.
AB - Physics-based simulations are often used to model and understand complex physical systems in domains such as fluid dynamics. Such simulations, although used frequently, often suffer from inaccurate or incomplete representations either due to their high computational costs or due to lack of complete physical knowledge of the system. In such situations, it is useful to employ machine learning (ML) to fill the gap by learning a model of the complex physical process directly from simulation data. However, as data generation through simulations is costly, we need to develop models being cognizant of data paucity issues. In such scenarios, it is helpful if the rich physical knowledge of the application domain is incorporated in the architectural design of ML models. We can also use information from physics-based simulations to guide the learning process using aggregate supervision to favorably constrain the learning process. In this article, we propose PhyNet, a deep learning model using physics-guided structural priors and physics-guided aggregate supervision for modeling the drag forces acting on each particle in a computational fluid dynamics-discrete element method. We conduct extensive experiments in the context of drag force prediction and showcase the usefulness of including physics knowledge in our deep learning formulation. PhyNet has been compared with several state-of-the-art models and achieves a significant performance improvement of 7.09% on average. The source code has been made available∗.
KW - computational fluid dynamics
KW - data mining
KW - machine learning
KW - physics-guided learning
UR - http://www.scopus.com/inward/record.url?scp=85094112054&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85094112054&partnerID=8YFLogxK
U2 - 10.1089/big.2020.0071
DO - 10.1089/big.2020.0071
M3 - Article
C2 - 33090021
AN - SCOPUS:85094112054
SN - 2167-6461
VL - 8
SP - 431
EP - 449
JO - Big Data
JF - Big Data
IS - 5
ER -