A general Neural Particle Method for hydrodynamics modeling

Jinshuai Bai; Ying Zhou; Yuwei Ma; Hyogu Jeong; Haifei Zhan; Charith Rathnayaka; Emilie Sauret; Yuantong Gu

doi:10.1016/j.cma.2022.114740

Back

A general Neural Particle Method for hydrodynamics modeling

Journal article

Peer reviewed

A general Neural Particle Method for hydrodynamics modeling

Jinshuai Bai, Ying Zhou, Yuwei Ma, Hyogu Jeong, Haifei Zhan, Charith Rathnayaka, Emilie Sauret and Yuantong Gu

Computer Methods in Applied Mechanics and Engineering, Vol.393, pp.1-21

2022

DOI: https://doi.org/10.1016/j.cma.2022.114740

Files and links (1)

url

https://doi.org/10.1016/j.cma.2022.114740View

Published Version

Abstract

Numerical modelling and mechanical characterisation

Machine learning

Computational methods in fluid flow, heat and mass transfer (incl. computational fluid dynamics)

Deep learning

Neural Particle Method

Physics-informed neural network

Hydrodynamics modeling

Meshfree method

Neural Particle Method (NPM) is a newly proposed Physics-Informed Neural Network (PINN) based, truly meshfree method for hydrodynamics modeling. In the NPM, PINN is applied to globally approximate field variables, and the high-order Implicit Runge–Kutta (IRK) method is used to treat the time integration. The NPM can easily achieve incompressibility and deal with the free-surface problem. However, the NPM is currently limited to inviscid hydrodynamics problems and is computationally expensive. In this work, we developed a general NPM (gNPM) for viscous hydrodynamics modeling. In the gNPM, a single pressure is output as the predicted pressure field rather than the multiple pressures in the original NPM. Thus, the size of the neural network is greatly reduced, making the gNPM computationally more efficient. Besides, the spatial derivatives in the governing equations are calculated with respect to the current spatial coordinates rather than the predicted space. In this manner, the gNPM is more straightforward to be implemented. Furthermore, by considering the viscous term in the conservation of momentum, the gNPM can be applied for viscous hydrodynamics modeling. The effectiveness and robustness of the gNPM have been demonstrated through several hydrodynamics benchmark cases with different boundary conditions. We highlight that the proposed gNPM is able to cope with highly uneven particle distributions, while the traditional meshfree method can produce severe failure.

Details

Title: A general Neural Particle Method for hydrodynamics modeling
Authors: Jinshuai Bai (Author) - Queensland University of Technology
Ying Zhou (Author) - Northwestern Polytechnical University
Yuwei Ma (Author) - Peking University
Hyogu Jeong (Author) - Queensland University of Technology
Haifei Zhan (Author) - Zhejiang University
Charith Rathnayaka (Author) - University of the Sunshine Coast, Queensland, School of Science, Technology and Engineering
Emilie Sauret (Author) - Queensland University of Technology
Yuantong Gu (Author) - Queensland University of Technology
Publication details: Computer Methods in Applied Mechanics and Engineering, Vol.393, pp.1-21
Publisher: Elsevier BV
DOI: 10.1016/j.cma.2022.114740
ISSN: 1879-2138
Grants: A Novel Multilevel Modelling Framework to Design Diamond Nanothread Bundles, DP200102546, Australian Research Council (Australia, Canberra) - ARC
ARC Industrial Transformation Training Centre for Joint Biomechanics, IC190100020, Australian Research Council (Australia, Canberra) - ARC
Organisation Unit: School of Science, Technology and Engineering; University of the Sunshine Coast, Queensland
Language: English
Record Identifier: 99617908902621
Output Type: Journal article

Metrics

77 Record Views

17 Times Cited - Web of Science

See more details

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration; International collaboration
Web Of Science research areas: Engineering, Multidisciplinary; Mathematics, Interdisciplinary Applications; Mechanics

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

Source: InCites