Current and emerging deep-learning methods for the simulation of fluid dynamics

M Lino, S Fotiadis, AA Bharath… - Proceedings of the …, 2023 - royalsocietypublishing.org
Over the last decade, deep learning (DL), a branch of machine learning, has experienced
rapid progress. Powerful tools for tasks that have been traditionally complex to automate …

PIGNN-CFD: A physics-informed graph neural network for rapid predicting urban wind field defined on unstructured mesh

X Shao, Z Liu, S Zhang, Z Zhao, C Hu - Building and Environment, 2023 - Elsevier
Urban wind field plays an important role in quantitative assessment of urban environment.
Compared to field measurement and wind tunnel experiment, Computational Fluid …

[HTML][HTML] Multi-scale rotation-equivariant graph neural networks for unsteady Eulerian fluid dynamics

M Lino, S Fotiadis, AA Bharath, CD Cantwell - Physics of Fluids, 2022 - pubs.aip.org
The simulation of fluid dynamics, typically by numerically solving partial differential
equations, is an essential tool in many areas of science and engineering. However, the high …

Surrogate modelling for an aircraft dynamic landing loads simulation using an LSTM AutoEncoder-based dimensionality reduction approach

M Lazzara, M Chevalier, M Colombo, JG Garcia… - Aerospace Science and …, 2022 - Elsevier
Surrogate modelling can alleviate the computational burden of design activities as they rely
on multiple evaluations of high-fidelity models. However, the learning task can be adversely …

Accurate and efficient urban wind prediction at city-scale with memory-scalable graph neural network

Z Liu, S Zhang, X Shao, Z Wu - Sustainable Cities and Society, 2023 - Elsevier
The interaction between buildings and wind significantly impacts the comfort and safety of
pedestrians, thereby influencing the sustainability of cities. Computational fluid dynamics …

[HTML][HTML] Inexpensive high fidelity melt pool models in additive manufacturing using generative deep diffusion

F Ogoke, Q Liu, O Ajenifujah, A Myers, G Quirarte… - Materials & Design, 2024 - Elsevier
Defects in laser powder bed fusion (L-PBF) parts often result from the meso-scale dynamics
of the molten alloy near the laser, known as the melt pool. For instance, the melt pool can …

On the use of graph neural networks and shape‐function‐based gradient computation in the deep energy method

J He, D Abueidda, S Koric… - International Journal for …, 2023 - Wiley Online Library
A graph convolutional network (GCN) is employed in the deep energy method (DEM) model
to solve the momentum balance equation in three‐dimensional space for the deformation of …

Grid adaptive reduced-order model of fluid flow based on graph convolutional neural network

JZ Peng, YZ Wang, S Chen, ZH Chen, WT Wu… - Physics of …, 2022 - pubs.aip.org
In the interdisciplinary field of data-driven models and computational fluid mechanics, the
reduced-order model for flow field prediction is mainly constructed by a convolutional neural …

Forecasting three-dimensional unsteady multi-phase flow fields in the coal-supercritical water fluidized bed reactor via graph neural networks

Y Hao, X Xie, P Zhao, X Wang, J Ding, R Xie, H Liu - Energy, 2023 - Elsevier
The study of three-dimensional unsteady multi-phase flows inside the coal-supercritical
water fluidized bed (SCWFB) reactor coupled with fluid dynamics, heat transfer and …

Self-supervised learning based on transformer for flow reconstruction and prediction

B Xu, Y Zhou, X Bian - Physics of Fluids, 2024 - pubs.aip.org
Machine learning has great potential for efficient reconstruction and prediction of flow fields.
However, existing datasets may have highly diversified labels for different flow scenarios …