Deep Learning for Fluid Simulation

A special issue of Fluids (ISSN 2311-5521). This special issue belongs to the section "Mathematical and Computational Fluid Mechanics".

Deadline for manuscript submissions: closed (31 May 2021) | Viewed by 9934

Special Issue Editor


E-Mail Website
Guest Editor
School of Computing, University of Leeds, Leeds LS2 9JT, UK
Interests: reduced order models for fluids; deep learning for fluid simulation; uncertainty quantification; cardiovascular flow modelling

Special Issue Information

Dear Colleagues,

Deep neural networks are increasingly used for data-driven acceleration of fluid dynamics simulations. These models can be understood as nonlinear approximation methods for reproducing high-dimensional input-output maps based on nested layers of linear filters and non-linear activation functions. The filter weights and other hyperparameters are learned from a large corpus of training data through a stochastic gradient descent algorithm. In the case of deep learning for fluid simulations, the models can be trained with either computational fluid dynamics simulation data or actual flow measurement data. Various approaches have been proposed for tackling fluid dynamics simulation by deep learning, such as encoder-decoder and generative adversarial networks, graph neural networks, and convolutional networks for both particle-based flow simulations as well as continuous velocity field approximations. Current challenges in this topic include incorporating physical constraints of fluids to neural networks, learning model structure from experimental fluid measurements, simulating complex particulate and multi-phase flows, and generalizing flow behavior from limited training data.

Dr. Toni Lassila
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Fluids is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Deep learning for fluids
  • Encoder-decoder networks
  • Generative adversarial networks
  • Graph neural networks
  • Physics-constrained neural networks
  • Data-driven modelling
  • Reduced order models

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

25 pages, 6978 KiB  
Article
Real-Time Simulation of Parameter-Dependent Fluid Flows through Deep Learning-Based Reduced Order Models
by Stefania Fresca and Andrea Manzoni
Fluids 2021, 6(7), 259; https://doi.org/10.3390/fluids6070259 - 18 Jul 2021
Cited by 31 | Viewed by 4907
Abstract
Simulating fluid flows in different virtual scenarios is of key importance in engineering applications. However, high-fidelity, full-order models relying, e.g., on the finite element method, are unaffordable whenever fluid flows must be simulated in almost real-time. Reduced order models (ROMs) relying, e.g., on [...] Read more.
Simulating fluid flows in different virtual scenarios is of key importance in engineering applications. However, high-fidelity, full-order models relying, e.g., on the finite element method, are unaffordable whenever fluid flows must be simulated in almost real-time. Reduced order models (ROMs) relying, e.g., on proper orthogonal decomposition (POD) provide reliable approximations to parameter-dependent fluid dynamics problems in rapid times. However, they might require expensive hyper-reduction strategies for handling parameterized nonlinear terms, and enriched reduced spaces (or Petrov–Galerkin projections) if a mixed velocity–pressure formulation is considered, possibly hampering the evaluation of reliable solutions in real-time. Dealing with fluid–structure interactions entails even greater difficulties. The proposed deep learning (DL)-based ROMs overcome all these limitations by learning, in a nonintrusive way, both the nonlinear trial manifold and the reduced dynamics. To do so, they rely on deep neural networks, after performing a former dimensionality reduction through POD, enhancing their training times substantially. The resulting POD-DL-ROMs are shown to provide accurate results in almost real-time for the flow around a cylinder benchmark, the fluid–structure interaction between an elastic beam attached to a fixed, rigid block and a laminar incompressible flow, and the blood flow in a cerebral aneurysm. Full article
(This article belongs to the Special Issue Deep Learning for Fluid Simulation)
Show Figures

Figure 1

14 pages, 3233 KiB  
Article
A Systematic Approach to Predict the Behavior of Cough Droplets Using Feedforward Neural Networks Method
by Irfan Bahiuddin, Setyawan Bekti Wibowo, M. Syairaji, Jimmy Trio Putra, Cahyo Adi Pandito, Ahdiar Fikri Maulana, Rian Mantasa Salve Prastica and Nurhazimah Nazmi
Fluids 2021, 6(2), 76; https://doi.org/10.3390/fluids6020076 - 9 Feb 2021
Cited by 3 | Viewed by 2407
Abstract
Coronavirus disease 2019 (Covid-19) has been identified as being transmitted among humans with droplets from breath, cough, and sneezes. Understanding the droplets’ behavior can be critical information to avoid disease transmission, especially while designing a device deals with human air respiratory. Although various [...] Read more.
Coronavirus disease 2019 (Covid-19) has been identified as being transmitted among humans with droplets from breath, cough, and sneezes. Understanding the droplets’ behavior can be critical information to avoid disease transmission, especially while designing a device deals with human air respiratory. Although various studies have provided enormous computational fluid simulations, most cases are too specific and quite challenging to combine with other similar studies directly. Therefore, this paper proposes a systematic approach to predict the droplet behavior for coughing cases using machine learning. The approach consists of three models, which are droplet generator, mask model, and free droplet model modeled using feedforward neural network (FFNN). The evaluation has shown that the three FFNNs models’ accuracies are relatively high, with R-values of more than 0.990. The model has successfully predicted the evaporation effect on the diameter reduction and the completely evaporated state, which can be considered unlearned cases for machine learning models. The predicted horizontal distance pattern also agrees with the data in the literature. In summary, the proposed approach has demonstrated the capability to predict the diameter pattern according to the experimental or previous work data at various mask face types. Full article
(This article belongs to the Special Issue Deep Learning for Fluid Simulation)
Show Figures

Figure 1

Back to TopTop